GraySoft
Projects Models Compare Cloud benchmarks FAQ Download guIDE →
Model Intelligence Sheet

unsloth/Inkling-Small-GGUF overview

Read our How to Run Inkling Guide https://unsloth.ai/docs/models/inkling <div <p style="margin: 0 0 0px 0; margin top: 0px;" <em See <a href="https://unsloth.a…

ggufconversationalimage-text-to-textaudio-text-to-textmoeunslothinkling_mm_modelbase_model:thinkingmachines/Inkling-Smallbase_model:quantized:thinkingmachines/Inkling-Smalllicense:apache-2.0endpoints_compatibleregion:us

Runs locally from ~12.4 MB disk (4 GB VRAM class GPUs with llama.cpp / guIDE).

Downloads
0
Likes
46
Pipeline
image-text-to-text
Author

Repository Files & Downloads

113 GGUF files detected
Direct downloads for local inference
FileTypeQuantizationSizeLink
BF16/Inkling-Small-BF16-00001-of-00011.ggufGGUFBF1644.43 GBDownload
BF16/Inkling-Small-BF16-00002-of-00011.ggufGGUFBF1644.74 GBDownload
BF16/Inkling-Small-BF16-00003-of-00011.ggufGGUFBF1645.11 GBDownload
BF16/Inkling-Small-BF16-00004-of-00011.ggufGGUFBF1645.06 GBDownload
BF16/Inkling-Small-BF16-00005-of-00011.ggufGGUFBF1644.82 GBDownload
BF16/Inkling-Small-BF16-00006-of-00011.ggufGGUFBF1644.73 GBDownload
BF16/Inkling-Small-BF16-00007-of-00011.ggufGGUFBF1646.55 GBDownload
BF16/Inkling-Small-BF16-00008-of-00011.ggufGGUFBF1644.71 GBDownload
BF16/Inkling-Small-BF16-00009-of-00011.ggufGGUFBF1644.66 GBDownload
BF16/Inkling-Small-BF16-00010-of-00011.ggufGGUFBF1646.18 GBDownload
BF16/Inkling-Small-BF16-00011-of-00011.ggufGGUFBF1640.21 GBDownload
MXFP4_MOE/Inkling-Small-MXFP4_MOE-00001-of-00005.ggufGGUFGGUF12.4 MBDownload
MXFP4_MOE/Inkling-Small-MXFP4_MOE-00002-of-00005.ggufGGUFGGUF45.33 GBDownload
MXFP4_MOE/Inkling-Small-MXFP4_MOE-00003-of-00005.ggufGGUFGGUF45.65 GBDownload
MXFP4_MOE/Inkling-Small-MXFP4_MOE-00004-of-00005.ggufGGUFGGUF45.68 GBDownload
MXFP4_MOE/Inkling-Small-MXFP4_MOE-00005-of-00005.ggufGGUFGGUF10.51 GBDownload
Q8_0/Inkling-Small-Q8_0-00001-of-00007.ggufGGUFQ8_012.4 MBDownload
Q8_0/Inkling-Small-Q8_0-00002-of-00007.ggufGGUFQ8_045.28 GBDownload
Q8_0/Inkling-Small-Q8_0-00003-of-00007.ggufGGUFQ8_045.31 GBDownload
Q8_0/Inkling-Small-Q8_0-00004-of-00007.ggufGGUFQ8_045.31 GBDownload
Q8_0/Inkling-Small-Q8_0-00005-of-00007.ggufGGUFQ8_045.31 GBDownload
Q8_0/Inkling-Small-Q8_0-00006-of-00007.ggufGGUFQ8_045.31 GBDownload
Q8_0/Inkling-Small-Q8_0-00007-of-00007.ggufGGUFQ8_034.50 GBDownload
UD-IQ1_M/Inkling-Small-UD-IQ1_M-00001-of-00003.ggufGGUFIQ1_M12.4 MBDownload
UD-IQ1_M/Inkling-Small-UD-IQ1_M-00002-of-00003.ggufGGUFIQ1_M46.27 GBDownload
UD-IQ1_M/Inkling-Small-UD-IQ1_M-00003-of-00003.ggufGGUFIQ1_M27.14 GBDownload
UD-IQ1_S/Inkling-Small-UD-IQ1_S-00001-of-00003.ggufGGUFIQ1_S12.4 MBDownload
UD-IQ1_S/Inkling-Small-UD-IQ1_S-00002-of-00003.ggufGGUFIQ1_S46.25 GBDownload
UD-IQ1_S/Inkling-Small-UD-IQ1_S-00003-of-00003.ggufGGUFIQ1_S23.37 GBDownload
UD-IQ2_M/Inkling-Small-UD-IQ2_M-00001-of-00003.ggufGGUFIQ2_M12.4 MBDownload
UD-IQ2_M/Inkling-Small-UD-IQ2_M-00002-of-00003.ggufGGUFIQ2_M46.09 GBDownload
UD-IQ2_M/Inkling-Small-UD-IQ2_M-00003-of-00003.ggufGGUFIQ2_M30.67 GBDownload
UD-IQ2_XXS/Inkling-Small-UD-IQ2_XXS-00001-of-00003.ggufGGUFIQ2_XXS12.4 MBDownload
UD-IQ2_XXS/Inkling-Small-UD-IQ2_XXS-00002-of-00003.ggufGGUFIQ2_XXS45.97 GBDownload
UD-IQ2_XXS/Inkling-Small-UD-IQ2_XXS-00003-of-00003.ggufGGUFIQ2_XXS30.66 GBDownload
UD-IQ3_S/Inkling-Small-UD-IQ3_S-00001-of-00004.ggufGGUFIQ3_S12.4 MBDownload
UD-IQ3_S/Inkling-Small-UD-IQ3_S-00002-of-00004.ggufGGUFIQ3_S46.31 GBDownload
UD-IQ3_S/Inkling-Small-UD-IQ3_S-00003-of-00004.ggufGGUFIQ3_S45.99 GBDownload
UD-IQ3_S/Inkling-Small-UD-IQ3_S-00004-of-00004.ggufGGUFIQ3_S7.77 GBDownload
UD-IQ3_XXS/Inkling-Small-UD-IQ3_XXS-00001-of-00003.ggufGGUFIQ3_XXS12.4 MBDownload
UD-IQ3_XXS/Inkling-Small-UD-IQ3_XXS-00002-of-00003.ggufGGUFIQ3_XXS46.02 GBDownload
UD-IQ3_XXS/Inkling-Small-UD-IQ3_XXS-00003-of-00003.ggufGGUFIQ3_XXS45.18 GBDownload
UD-IQ4_NL/Inkling-Small-UD-IQ4_NL-00001-of-00004.ggufGGUFIQ4_NL12.4 MBDownload
UD-IQ4_NL/Inkling-Small-UD-IQ4_NL-00002-of-00004.ggufGGUFIQ4_NL46.09 GBDownload
UD-IQ4_NL/Inkling-Small-UD-IQ4_NL-00003-of-00004.ggufGGUFIQ4_NL46.14 GBDownload
UD-IQ4_NL/Inkling-Small-UD-IQ4_NL-00004-of-00004.ggufGGUFIQ4_NL28.91 GBDownload
UD-IQ4_XS/Inkling-Small-UD-IQ4_XS-00001-of-00004.ggufGGUFIQ4_XS12.4 MBDownload
UD-IQ4_XS/Inkling-Small-UD-IQ4_XS-00002-of-00004.ggufGGUFIQ4_XS46.23 GBDownload
UD-IQ4_XS/Inkling-Small-UD-IQ4_XS-00003-of-00004.ggufGGUFIQ4_XS46.06 GBDownload
UD-IQ4_XS/Inkling-Small-UD-IQ4_XS-00004-of-00004.ggufGGUFIQ4_XS26.35 GBDownload
UD-Q2_K_XL/Inkling-Small-UD-Q2_K_XL-00001-of-00003.ggufGGUFQ2_K_XL12.4 MBDownload
UD-Q2_K_XL/Inkling-Small-UD-Q2_K_XL-00002-of-00003.ggufGGUFQ2_K_XL46.48 GBDownload
UD-Q2_K_XL/Inkling-Small-UD-Q2_K_XL-00003-of-00003.ggufGGUFQ2_K_XL35.41 GBDownload
UD-Q3_K_M/Inkling-Small-UD-Q3_K_M-00001-of-00004.ggufGGUFQ3_K_M12.4 MBDownload
UD-Q3_K_M/Inkling-Small-UD-Q3_K_M-00002-of-00004.ggufGGUFQ3_K_M45.93 GBDownload
UD-Q3_K_M/Inkling-Small-UD-Q3_K_M-00003-of-00004.ggufGGUFQ3_K_M46.54 GBDownload
UD-Q3_K_M/Inkling-Small-UD-Q3_K_M-00004-of-00004.ggufGGUFQ3_K_M18.68 GBDownload
UD-Q3_K_XL/Inkling-Small-UD-Q3_K_XL-00001-of-00004.ggufGGUFQ3_K_XL12.4 MBDownload
UD-Q3_K_XL/Inkling-Small-UD-Q3_K_XL-00002-of-00004.ggufGGUFQ3_K_XL46.11 GBDownload
UD-Q3_K_XL/Inkling-Small-UD-Q3_K_XL-00003-of-00004.ggufGGUFQ3_K_XL46.54 GBDownload
UD-Q3_K_XL/Inkling-Small-UD-Q3_K_XL-00004-of-00004.ggufGGUFQ3_K_XL18.68 GBDownload
UD-Q4_K_M/Inkling-Small-UD-Q4_K_M-00001-of-00005.ggufGGUFQ4_K_M12.4 MBDownload
UD-Q4_K_M/Inkling-Small-UD-Q4_K_M-00002-of-00005.ggufGGUFQ4_K_M45.46 GBDownload
UD-Q4_K_M/Inkling-Small-UD-Q4_K_M-00003-of-00005.ggufGGUFQ4_K_M45.86 GBDownload
UD-Q4_K_M/Inkling-Small-UD-Q4_K_M-00004-of-00005.ggufGGUFQ4_K_M46.06 GBDownload
UD-Q4_K_M/Inkling-Small-UD-Q4_K_M-00005-of-00005.ggufGGUFQ4_K_M13.99 GBDownload
UD-Q4_K_S/Inkling-Small-UD-Q4_K_S-00001-of-00005.ggufGGUFQ4_K_S12.4 MBDownload
UD-Q4_K_S/Inkling-Small-UD-Q4_K_S-00002-of-00005.ggufGGUFQ4_K_S45.93 GBDownload
UD-Q4_K_S/Inkling-Small-UD-Q4_K_S-00003-of-00005.ggufGGUFQ4_K_S46.33 GBDownload
UD-Q4_K_S/Inkling-Small-UD-Q4_K_S-00004-of-00005.ggufGGUFQ4_K_S45.66 GBDownload
UD-Q4_K_S/Inkling-Small-UD-Q4_K_S-00005-of-00005.ggufGGUFQ4_K_S3.94 GBDownload
UD-Q4_K_XL/Inkling-Small-UD-Q4_K_XL-00001-of-00005.ggufGGUFQ4_K_XL12.4 MBDownload
UD-Q4_K_XL/Inkling-Small-UD-Q4_K_XL-00002-of-00005.ggufGGUFQ4_K_XL45.64 GBDownload
UD-Q4_K_XL/Inkling-Small-UD-Q4_K_XL-00003-of-00005.ggufGGUFQ4_K_XL45.86 GBDownload
UD-Q4_K_XL/Inkling-Small-UD-Q4_K_XL-00004-of-00005.ggufGGUFQ4_K_XL46.06 GBDownload
UD-Q4_K_XL/Inkling-Small-UD-Q4_K_XL-00005-of-00005.ggufGGUFQ4_K_XL14.49 GBDownload
UD-Q5_K_M/Inkling-Small-UD-Q5_K_M-00001-of-00005.ggufGGUFQ5_K_M12.4 MBDownload
UD-Q5_K_M/Inkling-Small-UD-Q5_K_M-00002-of-00005.ggufGGUFQ5_K_M45.61 GBDownload
UD-Q5_K_M/Inkling-Small-UD-Q5_K_M-00003-of-00005.ggufGGUFQ5_K_M46.32 GBDownload
UD-Q5_K_M/Inkling-Small-UD-Q5_K_M-00004-of-00005.ggufGGUFQ5_K_M46.54 GBDownload
UD-Q5_K_M/Inkling-Small-UD-Q5_K_M-00005-of-00005.ggufGGUFQ5_K_M44.15 GBDownload
UD-Q5_K_S/Inkling-Small-UD-Q5_K_S-00001-of-00005.ggufGGUFQ5_K_S12.4 MBDownload
UD-Q5_K_S/Inkling-Small-UD-Q5_K_S-00002-of-00005.ggufGGUFQ5_K_S45.78 GBDownload
UD-Q5_K_S/Inkling-Small-UD-Q5_K_S-00003-of-00005.ggufGGUFQ5_K_S46.45 GBDownload
UD-Q5_K_S/Inkling-Small-UD-Q5_K_S-00004-of-00005.ggufGGUFQ5_K_S46.45 GBDownload
UD-Q5_K_S/Inkling-Small-UD-Q5_K_S-00005-of-00005.ggufGGUFQ5_K_S32.88 GBDownload
UD-Q5_K_XL/Inkling-Small-UD-Q5_K_XL-00001-of-00005.ggufGGUFQ5_K_XL12.4 MBDownload
UD-Q5_K_XL/Inkling-Small-UD-Q5_K_XL-00002-of-00005.ggufGGUFQ5_K_XL45.61 GBDownload
UD-Q5_K_XL/Inkling-Small-UD-Q5_K_XL-00003-of-00005.ggufGGUFQ5_K_XL46.32 GBDownload
UD-Q5_K_XL/Inkling-Small-UD-Q5_K_XL-00004-of-00005.ggufGGUFQ5_K_XL46.54 GBDownload
UD-Q5_K_XL/Inkling-Small-UD-Q5_K_XL-00005-of-00005.ggufGGUFQ5_K_XL44.68 GBDownload
UD-Q6_K/Inkling-Small-UD-Q6_K-00001-of-00006.ggufGGUFQ6_K12.4 MBDownload
UD-Q6_K/Inkling-Small-UD-Q6_K-00002-of-00006.ggufGGUFQ6_K45.63 GBDownload
UD-Q6_K/Inkling-Small-UD-Q6_K-00003-of-00006.ggufGGUFQ6_K45.17 GBDownload
UD-Q6_K/Inkling-Small-UD-Q6_K-00004-of-00006.ggufGGUFQ6_K45.17 GBDownload
UD-Q6_K/Inkling-Small-UD-Q6_K-00005-of-00006.ggufGGUFQ6_K45.17 GBDownload
UD-Q6_K/Inkling-Small-UD-Q6_K-00006-of-00006.ggufGGUFQ6_K22.70 GBDownload
UD-Q6_K_XL/Inkling-Small-UD-Q6_K_XL-00001-of-00006.ggufGGUFQ6_K_XL12.4 MBDownload
UD-Q6_K_XL/Inkling-Small-UD-Q6_K_XL-00002-of-00006.ggufGGUFQ6_K_XL46.19 GBDownload
UD-Q6_K_XL/Inkling-Small-UD-Q6_K_XL-00003-of-00006.ggufGGUFQ6_K_XL46.17 GBDownload
UD-Q6_K_XL/Inkling-Small-UD-Q6_K_XL-00004-of-00006.ggufGGUFQ6_K_XL45.69 GBDownload
UD-Q6_K_XL/Inkling-Small-UD-Q6_K_XL-00005-of-00006.ggufGGUFQ6_K_XL45.73 GBDownload
UD-Q6_K_XL/Inkling-Small-UD-Q6_K_XL-00006-of-00006.ggufGGUFQ6_K_XL39.45 GBDownload
UD-Q8_K_XL/Inkling-Small-UD-Q8_K_XL-00001-of-00007.ggufGGUFQ8_K_XL12.4 MBDownload
UD-Q8_K_XL/Inkling-Small-UD-Q8_K_XL-00002-of-00007.ggufGGUFQ8_K_XL45.28 GBDownload
UD-Q8_K_XL/Inkling-Small-UD-Q8_K_XL-00003-of-00007.ggufGGUFQ8_K_XL45.31 GBDownload
UD-Q8_K_XL/Inkling-Small-UD-Q8_K_XL-00004-of-00007.ggufGGUFQ8_K_XL45.31 GBDownload
UD-Q8_K_XL/Inkling-Small-UD-Q8_K_XL-00005-of-00007.ggufGGUFQ8_K_XL45.31 GBDownload
UD-Q8_K_XL/Inkling-Small-UD-Q8_K_XL-00006-of-00007.ggufGGUFQ8_K_XL45.31 GBDownload
UD-Q8_K_XL/Inkling-Small-UD-Q8_K_XL-00007-of-00007.ggufGGUFQ8_K_XL42.09 GBDownload
mmproj-BF16.ggufGGUFBF16132.3 MBDownload
mmproj-F16.ggufGGUFF16132.3 MBDownload
mmproj-F32.ggufGGUFF32264.5 MBDownload

Model Details

Model IDunsloth/Inkling-Small-GGUF
Authorunsloth
Pipelineimage-text-to-text
Licenseapache-2.0
Base modelthinkingmachines/Inkling-Small
Last modified2026-07-31T03:56:12.000Z

Model README

---

license: apache-2.0

license_link: https://www.apache.org/licenses/LICENSE-2.0

pipeline_tag: image-text-to-text

tags:

  • conversational
  • image-text-to-text
  • audio-text-to-text
  • moe
  • unsloth
  • inkling_mm_model

base_model:

  • thinkingmachines/Inkling-Small

---

Read our How to Run Inkling Guide!

<div>

<p style="margin: 0 0 0px 0; margin-top: 0px;">

<em>See <a href="https://unsloth.ai/docs/basics/unsloth-dynamic-v2.0-gguf">Unsloth Dynamic 2.0 GGUFs</a> for our quantization benchmarks.</em>

</p>

<div style="display: flex; gap: 5px; align-items: center; margin-bottom: 0px;">

<a href="https://github.com/unslothai/unsloth/">

<img src="https://github.com/unslothai/unsloth/raw/main/images/unsloth%20new%20logo.png" width="133">

</a>

<a href="https://discord.gg/unsloth">

<img src="https://github.com/unslothai/unsloth/raw/main/images/Discord%20button.png" width="173">

</a>

<a href="https://unsloth.ai/docs/models/inkling">

<img src="https://raw.githubusercontent.com/unslothai/unsloth/refs/heads/main/images/documentation%20green%20button.png" width="143">

</a>

</div>

<ul style="margin: 0;">

<li>You can now run Inkling in <a href="https://github.com/unslothai/unsloth/">Unsloth Studio</a> with toggles for Thinking.</li>

<li>Read our <a href="https://unsloth.ai/docs/models/inkling">Inkling guide</a> for analysis and instructions.</li>

<li>See below for example of <b>1-bit UD-IQ1_S</b> GGUF running in Unsloth:</li>

</ul>

</div>

<img width="600" alt="Inkling in unsloth studio" src="https://cdn-uploads.huggingface.co/production/uploads/62ecdc18b72a69615d6bd857/gvmCZ7Lotw8AtazdT5FYP.gif" />

---

Inkling

<img src="https://cdn-uploads.huggingface.co/production/uploads/630e8f0bf6f6d700f50ebd2e/AvmDwmrWRMnKjOWvmLieg.png" style="display: block;margin-left: auto;margin-right: auto;width: 30%;">

<p align="center">

<a href="https://huggingface.co/thinkingmachines/Inkling-Small">BF16</a> |

<a href="https://huggingface.co/thinkingmachines/Inkling-Small-NVFP4">NVFP4</a> |

<a href="https://tinker.thinkingmachines.ai/playground">Playground</a> |

<a href="https://github.com/thinking-machines-lab/tinker-cookbook">Tinker Cookbook</a> |

<a href="https://thinkingmachines.ai/model-acceptable-use-policy">Acceptable Use</a>

</p>

1. General Information

Inkling-Small is a general-purpose multimodal model that accepts text, image and audio inputs and generates text outputs. It is intended for use in English and other languages, and across multiple coding languages. The model is designed to be used by developers building AI-powered applications, including agentic and tool-use systems, coding assistants, chatbots, and retrieval-augmented generation systems, and is suitable for general-purpose conversational use, instruction-following, and other natural language and multimodal tasks. It is released with open weights to support research, fine-tuning and integration into third-party products by downstream developers.

Languages: English, with general multilingual capabilities across other languages.

2. Getting Started

Try Inkling-Small on the Tinker Playground or access via API using the Tinker Cookbook.

Inkling-Small supports local deployment using the following open-source libraries:

API access is also available through third party inference providers.

3. Model Properties

Model type

Multimodal autoregressive transformer

Architecture type

A 42-layer decoder-only transformer with a sparse Mixture-of-Experts (MoE) feed-forward backbone: each token is routed to 6 of 256 experts, plus 2 shared experts active on every token. Attention is a hybrid of local and global layers. The model is natively multimodal — images are encoded via a hierarchical patch encoder, and audio via discrete token encoding — with all modalities projected into a shared hidden space and processed jointly by the decoder.

Parameters

276B total, 12B active

Numerics support

BF16 and NVFP4

Input modalities

Inkling-Small accepts text, image, and audio inputs:

  • Text: UTF-8 encoded text
  • Image: Any pixel-based image input. For optimal performance, each image dimension should be between 40px to 4096px.
  • Audio: WAV format, sampled at 16kHz. For optimal performance, audio length should ideally be under 2 mins.

Output modalities

Inkling-Small generates output as UTF-8 encoded text.

4. Training

Training data includes a broad variety of content types, including text, images, audio, video.

Training data for the model was drawn from publicly available sources, acquired from third-parties, or synthetically generated or augmented. Publicly available data includes content from the public internet and publicly accessible repositories.

The training data curation process includes cleaning, processing, and modifying datasets. These processing steps, which vary by data type, may include deduplication and filtering to remove junk or other low-quality data, or to advance safety or other objectives.

5. Evaluations

<table style="border-collapse: separate; border-spacing: 0px; font-size: 11.1304px; line-height: 1.35; color: rgb(26, 26, 26); width: max-content;"><thead><tr><th aria-hidden="true" style="padding: 0.470903rem 0.68495rem; border-bottom-width: medium; border-bottom-style: none; border-bottom-color: currentcolor;"></th><th colspan="7" style="padding: 0.329632rem 0.770569rem 0.659264rem; text-align: center; font-weight: 500; font-size: 1em; color: rgb(107, 107, 107); white-space: normal; vertical-align: bottom; border-bottom-width: medium; border-bottom-style: none; border-bottom-color: currentcolor;">Open weights</th><th colspan="3" style="padding: 0.329632rem 0.770569rem 0.659264rem; text-align: center; font-weight: 500; font-size: 1em; color: rgb(107, 107, 107); white-space: normal; vertical-align: bottom; border-bottom-width: medium; border-bottom-style: none; border-bottom-color: currentcolor;">Closed weights</th></tr><tr><th aria-hidden="true" style="padding: 0.470903rem 0.68495rem; border-bottom: 1px solid rgba(0, 0, 0, 0.12);"></th><th style="padding: 0.470903rem 0.770569rem; text-align: center; font-weight: 500; color: rgb(26, 26, 26); white-space: normal; max-width: 113.017px; vertical-align: bottom; border-width: 1.5px 1.5px 1px; border-style: solid; border-color: rgba(0, 0, 0, 0.16) rgba(0, 0, 0, 0.16) rgba(0, 0, 0, 0.12); border-top-left-radius: 0.55rem; border-top-right-radius: 0.55rem;"><div>Inkling-Small</div></th><th style="padding: 0.470903rem 0.770569rem; text-align: center; font-weight: 400; color: rgb(26, 26, 26); white-space: normal; max-width: 113.017px; vertical-align: bottom; border-bottom: 1px solid rgba(0, 0, 0, 0.12);"><div>Qwen3.5-397B-A17B</div></th><th style="padding: 0.470903rem 0.770569rem; text-align: center; font-weight: 400; color: rgb(26, 26, 26); white-space: normal; max-width: 113.017px; vertical-align: bottom; border-bottom: 1px solid rgba(0, 0, 0, 0.12);"><div>MiMo V2.5</div></th><th style="padding: 0.470903rem 0.770569rem; text-align: center; font-weight: 400; color: rgb(26, 26, 26); white-space: normal; max-width: 113.017px; vertical-align: bottom; border-bottom: 1px solid rgba(0, 0, 0, 0.12);"><div>Minimax M2.7</div></th><th style="padding: 0.470903rem 0.770569rem; text-align: center; font-weight: 400; color: rgb(26, 26, 26); white-space: normal; max-width: 113.017px; vertical-align: bottom; border-bottom: 1px solid rgba(0, 0, 0, 0.12);"><div>DeepSeek V4 Flash</div></th><th style="padding: 0.470903rem 0.770569rem; text-align: center; font-weight: 400; color: rgb(26, 26, 26); white-space: normal; max-width: 113.017px; vertical-align: bottom; border-bottom: 1px solid rgba(0, 0, 0, 0.12);"><div>Nemotron 3 Ultra</div></th><th style="padding: 0.470903rem 0.770569rem; text-align: center; font-weight: 400; color: rgb(26, 26, 26); white-space: normal; max-width: 113.017px; vertical-align: bottom; border-bottom: 1px solid rgba(0, 0, 0, 0.12);"><div>Inkling</div></th><th style="padding: 0.470903rem 0.770569rem; text-align: center; font-weight: 400; color: rgb(26, 26, 26); white-space: normal; max-width: 113.017px; vertical-align: bottom; border-bottom: 1px solid rgba(0, 0, 0, 0.12); border-left: 1px solid rgba(0, 0, 0, 0.12);"><div>Claude 4.5 Haiku</div></th><th style="padding: 0.470903rem 0.770569rem; text-align: center; font-weight: 400; color: rgb(26, 26, 26); white-space: normal; max-width: 113.017px; vertical-align: bottom; border-bottom: 1px solid rgba(0, 0, 0, 0.12);"><div>Gemini 3.5 Flash-Lite</div></th><th style="padding: 0.470903rem 0.770569rem; text-align: center; font-weight: 400; color: rgb(26, 26, 26); white-space: normal; max-width: 113.017px; vertical-align: bottom; border-bottom: 1px solid rgba(0, 0, 0, 0.12);"><div>GPT 5.6 Luna</div></th></tr></thead><tbody><tr><th scope="row" style="padding: 0.27398rem 0.68495rem; text-align: left; font-size: 0.92em; font-weight: 400; line-height: 1.2; color: rgb(107, 107, 107); background: rgb(242, 242, 242); white-space: nowrap;">Model Info</th><td aria-hidden="true" style="padding: 0.27398rem 0.770569rem; background: rgb(242, 242, 242); border-left: 1.5px solid rgba(0, 0, 0, 0.16); border-right: 1.5px solid rgba(0, 0, 0, 0.16);"></td><td aria-hidden="true" style="padding: 0.27398rem 0.770569rem; background: rgb(242, 242, 242);"></td><td aria-hidden="true" style="padding: 0.27398rem 0.770569rem; background: rgb(242, 242, 242);"></td><td aria-hidden="true" style="padding: 0.27398rem 0.770569rem; background: rgb(242, 242, 242);"></td><td aria-hidden="true" style="padding: 0.27398rem 0.770569rem; background: rgb(242, 242, 242);"></td><td aria-hidden="true" style="padding: 0.27398rem 0.770569rem; background: rgb(242, 242, 242);"></td><td aria-hidden="true" style="padding: 0.27398rem 0.770569rem; background: rgb(242, 242, 242);"></td><td aria-hidden="true" style="padding: 0.27398rem 0.770569rem; background: rgb(242, 242, 242); border-left: 1px solid rgba(0, 0, 0, 0.12);"></td><td aria-hidden="true" style="padding: 0.27398rem 0.770569rem; background: rgb(242, 242, 242);"></td><td aria-hidden="true" style="padding: 0.27398rem 0.770569rem; background: rgb(242, 242, 242);"></td></tr><tr><td style="padding: 0.470903rem 0.68495rem; text-align: left; vertical-align: middle; max-width: 188.361px; border-bottom: 1px solid rgba(0, 0, 0, 0.12);"><span style="display: block; line-height: 1.22; white-space: nowrap;">AA Index (v4.1)</span><span style="display: block; font-size: 0.88em; line-height: 1.25; color: rgb(107, 107, 107); margin-top: 0.18rem; white-space: normal;">Score</span></td><td style="padding: 0.470903rem 0.770569rem; text-align: center; vertical-align: middle; font-variant-numeric: tabular-nums; font-weight: 500; border-bottom: 1px solid rgba(0, 0, 0, 0.12); border-left: 1.5px solid rgba(0, 0, 0, 0.16); border-right: 1.5px solid rgba(0, 0, 0, 0.16);">40.0%</td><td style="padding: 0.470903rem 0.770569rem; text-align: center; vertical-align: middle; font-variant-numeric: tabular-nums; font-weight: 400; border-bottom: 1px solid rgba(0, 0, 0, 0.12);">34.0%</td><td style="padding: 0.470903rem 0.770569rem; text-align: center; vertical-align: middle; font-variant-numeric: tabular-nums; font-weight: 400; border-bottom: 1px solid rgba(0, 0, 0, 0.12);">37.0%</td><td style="padding: 0.470903rem 0.770569rem; text-align: center; vertical-align: middle; font-variant-numeric: tabular-nums; font-weight: 400; border-bottom: 1px solid rgba(0, 0, 0, 0.12);">38.0%</td><td style="padding: 0.470903rem 0.770569rem; text-align: center; vertical-align: middle; font-variant-numeric: tabular-nums; font-weight: 400; border-bottom: 1px solid rgba(0, 0, 0, 0.12);">40.0%</td><td style="padding: 0.470903rem 0.770569rem; text-align: center; vertical-align: middle; font-variant-numeric: tabular-nums; font-weight: 400; border-bottom: 1px solid rgba(0, 0, 0, 0.12);">38.0%</td><td style="padding: 0.470903rem 0.770569rem; text-align: center; vertical-align: middle; font-variant-numeric: tabular-nums; font-weight: 400; border-bottom: 1px solid rgba(0, 0, 0, 0.12);">41.0%</td><td style="padding: 0.470903rem 0.770569rem; text-align: center; vertical-align: middle; font-variant-numeric: tabular-nums; font-weight: 400; border-bottom: 1px solid rgba(0, 0, 0, 0.12); border-left: 1px solid rgba(0, 0, 0, 0.12);">30.0%</td><td style="padding: 0.470903rem 0.770569rem; text-align: center; vertical-align: middle; font-variant-numeric: tabular-nums; font-weight: 400; border-bottom: 1px solid rgba(0, 0, 0, 0.12);">36.0%</td><td style="padding: 0.470903rem 0.770569rem; text-align: center; vertical-align: middle; font-variant-numeric: tabular-nums; font-weight: 500; background: rgb(251, 236, 191); border-bottom: 1px solid rgba(0, 0, 0, 0.12);">49.0%</td></tr><tr><td style="padding: 0.470903rem 0.68495rem; text-align: left; vertical-align: middle; max-width: 188.361px; border-bottom: 1px solid rgba(0, 0, 0, 0.12);"><span style="display: block; line-height: 1.22; white-space: nowrap;">Activated Params (B)</span><span style="display: block; font-size: 0.88em; line-height: 1.25; color: rgb(107, 107, 107); margin-top: 0.18rem; white-space: normal;">Score</span></td><td style="padding: 0.470903rem 0.770569rem; text-align: center; vertical-align: middle; font-variant-numeric: tabular-nums; font-weight: 500; border-bottom: 1px solid rgba(0, 0, 0, 0.12); border-left: 1.5px solid rgba(0, 0, 0, 0.16); border-right: 1.5px solid rgba(0, 0, 0, 0.16);">12</td><td style="padding: 0.470903rem 0.770569rem; text-align: center; vertical-align: middle; font-variant-numeric: tabular-nums; font-weight: 400; border-bottom: 1px solid rgba(0, 0, 0, 0.12);">17</td><td style="padding: 0.470903rem 0.770569rem; text-align: center; vertical-align: middle; font-variant-numeric: tabular-nums; font-weight: 400; border-bottom: 1px solid rgba(0, 0, 0, 0.12);">15</td><td style="padding: 0.470903rem 0.770569rem; text-align: center; vertical-align: middle; font-variant-numeric: tabular-nums; font-weight: 400; border-bottom: 1px solid rgba(0, 0, 0, 0.12);">10</td><td style="padding: 0.470903rem 0.770569rem; text-align: center; vertical-align: middle; font-variant-numeric: tabular-nums; font-weight: 400; border-bottom: 1px solid rgba(0, 0, 0, 0.12);">13</td><td style="padding: 0.470903rem 0.770569rem; text-align: center; vertical-align: middle; font-variant-numeric: tabular-nums; font-weight: 500; background: rgb(251, 236, 191); border-bottom: 1px solid rgba(0, 0, 0, 0.12);">55</td><td style="padding: 0.470903rem 0.770569rem; text-align: center; vertical-align: middle; font-variant-numeric: tabular-nums; font-weight: 400; border-bottom: 1px solid rgba(0, 0, 0, 0.12);">41</td><td style="padding: 0.470903rem 0.770569rem; text-align: center; vertical-align: middle; font-variant-numeric: tabular-nums; font-weight: 400; border-bottom: 1px solid rgba(0, 0, 0, 0.12); border-left: 1px solid rgba(0, 0, 0, 0.12);">–</td><td style="padding: 0.470903rem 0.770569rem; text-align: center; vertical-align: middle; font-variant-numeric: tabular-nums; font-weight: 400; border-bottom: 1px solid rgba(0, 0, 0, 0.12);">–</td><td style="padding: 0.470903rem 0.770569rem; text-align: center; vertical-align: middle; font-variant-numeric: tabular-nums; font-weight: 400; border-bottom: 1px solid rgba(0, 0, 0, 0.12);">–</td></tr><tr><td style="padding: 0.470903rem 0.68495rem; text-align: left; vertical-align: middle; max-width: 188.361px; border-bottom: 1px solid rgba(0, 0, 0, 0.12);"><span style="display: block; line-height: 1.22; white-space: nowrap;">Total Params (B)</span><span style="display: block; font-size: 0.88em; line-height: 1.25; color: rgb(107, 107, 107); margin-top: 0.18rem; white-space: normal;">Score</span></td><td style="padding: 0.470903rem 0.770569rem; text-align: center; vertical-align: middle; font-variant-numeric: tabular-nums; font-weight: 500; border-bottom: 1px solid rgba(0, 0, 0, 0.12); border-left: 1.5px solid rgba(0, 0, 0, 0.16); border-right: 1.5px solid rgba(0, 0, 0, 0.16);">276</td><td style="padding: 0.470903rem 0.770569rem; text-align: center; vertical-align: middle; font-variant-numeric: tabular-nums; font-weight: 400; border-bottom: 1px solid rgba(0, 0, 0, 0.12);">397</td><td style="padding: 0.470903rem 0.770569rem; text-align: center; vertical-align: middle; font-variant-numeric: tabular-nums; font-weight: 400; border-bottom: 1px solid rgba(0, 0, 0, 0.12);">310</td><td style="padding: 0.470903rem 0.770569rem; text-align: center; vertical-align: middle; font-variant-numeric: tabular-nums; font-weight: 400; border-bottom: 1px solid rgba(0, 0, 0, 0.12);">230</td><td style="padding: 0.470903rem 0.770569rem; text-align: center; vertical-align: middle; font-variant-numeric: tabular-nums; font-weight: 400; border-bottom: 1px solid rgba(0, 0, 0, 0.12);">284</td><td style="padding: 0.470903rem 0.770569rem; text-align: center; vertical-align: middle; font-variant-numeric: tabular-nums; font-weight: 400; border-bottom: 1px solid rgba(0, 0, 0, 0.12);">550</td><td style="padding: 0.470903rem 0.770569rem; text-align: center; vertical-align: middle; font-variant-numeric: tabular-nums; font-weight: 500; background: rgb(251, 236, 191); border-bottom: 1px solid rgba(0, 0, 0, 0.12);">975</td><td style="padding: 0.470903rem 0.770569rem; text-align: center; vertical-align: middle; font-variant-numeric: tabular-nums; font-weight: 400; border-bottom: 1px solid rgba(0, 0, 0, 0.12); border-left: 1px solid rgba(0, 0, 0, 0.12);">–</td><td style="padding: 0.470903rem 0.770569rem; text-align: center; vertical-align: middle; font-variant-numeric: tabular-nums; font-weight: 400; border-bottom: 1px solid rgba(0, 0, 0, 0.12);">–</td><td style="padding: 0.470903rem 0.770569rem; text-align: center; vertical-align: middle; font-variant-numeric: tabular-nums; font-weight: 400; border-bottom: 1px solid rgba(0, 0, 0, 0.12);">–</td></tr><tr><td style="padding: 0.470903rem 0.68495rem; text-align: left; vertical-align: middle; max-width: 188.361px; border-bottom: 1px solid rgba(0, 0, 0, 0.12);"><span style="display: block; line-height: 1.22; white-space: nowrap;">Pricing ($/M)</span><span style="display: block; font-size: 0.88em; line-height: 1.25; color: rgb(107, 107, 107); margin-top: 0.18rem; white-space: normal;">Input</span></td><td style="padding: 0.470903rem 0.770569rem; text-align: center; vertical-align: middle; font-variant-numeric: tabular-nums; font-weight: 500; border-bottom: 1px solid rgba(0, 0, 0, 0.12); border-left: 1.5px solid rgba(0, 0, 0, 0.16); border-right: 1.5px solid rgba(0, 0, 0, 0.16);">0.3</td><td style="padding: 0.470903rem 0.770569rem; text-align: center; vertical-align: middle; font-variant-numeric: tabular-nums; font-weight: 400; border-bottom: 1px solid rgba(0, 0, 0, 0.12);">0.39</td><td style="padding: 0.470903rem 0.770569rem; text-align: center; vertical-align: middle; font-variant-numeric: tabular-nums; font-weight: 500; background: rgb(251, 236, 191); border-bottom: 1px solid rgba(0, 0, 0, 0.12);">0.14</td><td style="padding: 0.470903rem 0.770569rem; text-align: center; vertical-align: middle; font-variant-numeric: tabular-nums; font-weight: 400; border-bottom: 1px solid rgba(0, 0, 0, 0.12);">0.25</td><td style="padding: 0.470903rem 0.770569rem; text-align: center; vertical-align: middle; font-variant-numeric: tabular-nums; font-weight: 500; background: rgb(251, 236, 191); border-bottom: 1px solid rgba(0, 0, 0, 0.12);">0.14</td><td style="padding: 0.470903rem 0.770569rem; text-align: center; vertical-align: middle; font-variant-numeric: tabular-nums; font-weight: 400; border-bottom: 1px solid rgba(0, 0, 0, 0.12);">0.5</td><td style="padding: 0.470903rem 0.770569rem; text-align: center; vertical-align: middle; font-variant-numeric: tabular-nums; font-weight: 400; border-bottom: 1px solid rgba(0, 0, 0, 0.12);">1</td><td style="padding: 0.470903rem 0.770569rem; text-align: center; vertical-align: middle; font-variant-numeric: tabular-nums; font-weight: 400; border-bottom: 1px solid rgba(0, 0, 0, 0.12); border-left: 1px solid rgba(0, 0, 0, 0.12);">1</td><td style="padding: 0.470903rem 0.770569rem; text-align: center; vertical-align: middle; font-variant-numeric: tabular-nums; font-weight: 400; border-bottom: 1px solid rgba(0, 0, 0, 0.12);">0.3</td><td style="padding: 0.470903rem 0.770569rem; text-align: center; vertical-align: middle; font-variant-numeric: tabular-nums; font-weight: 400; border-bottom: 1px solid rgba(0, 0, 0, 0.12);">0.5</td></tr><tr><td style="padding: 0.470903rem 0.68495rem; text-align: left; vertical-align: middle; max-width: 188.361px; border-bottom: 1px solid rgba(0, 0, 0, 0.12);"><span style="display: block; line-height: 1.22; white-space: nowrap;">Pricing ($/M)</span><span style="display: block; font-size: 0.88em; line-height: 1.25; color: rgb(107, 107, 107); margin-top: 0.18rem; white-space: normal;">Output</span></td><td style="padding: 0.470903rem 0.770569rem; text-align: center; vertical-align: middle; font-variant-numeric: tabular-nums; font-weight: 500; border-bottom: 1px solid rgba(0, 0, 0, 0.12); border-left: 1.5px solid rgba(0, 0, 0, 0.16); border-right: 1.5px solid rgba(0, 0, 0, 0.16);">1.2</td><td style="padding: 0.470903rem 0.770569rem; text-align: center; vertical-align: middle; font-variant-numeric: tabular-nums; font-weight: 400; border-bottom: 1px solid rgba(0, 0, 0, 0.12);">2.34</td><td style="padding: 0.470903rem 0.770569rem; text-align: center; vertical-align: middle; font-variant-numeric: tabular-nums; font-weight: 500; background: rgb(251, 236, 191); border-bottom: 1px solid rgba(0, 0, 0, 0.12);">0.28</td><td style="padding: 0.470903rem 0.770569rem; text-align: center; vertical-align: middle; font-variant-numeric: tabular-nums; font-weight: 400; border-bottom: 1px solid rgba(0, 0, 0, 0.12);">1</td><td style="padding: 0.470903rem 0.770569rem; text-align: center; vertical-align: middle; font-variant-numeric: tabular-nums; font-weight: 500; background: rgb(251, 236, 191); border-bottom: 1px solid rgba(0, 0, 0, 0.12);">0.28</td><td style="padding: 0.470903rem 0.770569rem; text-align: center; vertical-align: middle; font-variant-numeric: tabular-nums; font-weight: 400; border-bottom: 1px solid rgba(0, 0, 0, 0.12);">2.2</td><td style="padding: 0.470903rem 0.770569rem; text-align: center; vertical-align: middle; font-variant-numeric: tabular-nums; font-weight: 400; border-bottom: 1px solid rgba(0, 0, 0, 0.12);">4.05</td><td style="padding: 0.470903rem 0.770569rem; text-align: center; vertical-align: middle; font-variant-numeric: tabular-nums; font-weight: 400; border-bottom: 1px solid rgba(0, 0, 0, 0.12); border-left: 1px solid rgba(0, 0, 0, 0.12);">5</td><td style="padding: 0.470903rem 0.770569rem; text-align: center; vertical-align: middle; font-variant-numeric: tabular-nums; font-weight: 400; border-bottom: 1px solid rgba(0, 0, 0, 0.12);">2.5</td><td style="padding: 0.470903rem 0.770569rem; text-align: center; vertical-align: middle; font-variant-numeric: tabular-nums; font-weight: 400; border-bottom: 1px solid rgba(0, 0, 0, 0.12);">3</td></tr><tr><th scope="row" style="padding: 0.27398rem 0.68495rem; text-align: left; font-size: 0.92em; font-weight: 400; line-height: 1.2; color: rgb(107, 107, 107); background: rgb(242, 242, 242); white-space: nowrap;">Agentic (coding)</th><td aria-hidden="true" style="padding: 0.27398rem 0.770569rem; background: rgb(242, 242, 242); border-left: 1.5px solid rgba(0, 0, 0, 0.16); border-right: 1.5px solid rgba(0, 0, 0, 0.16);"></td><td aria-hidden="true" style="padding: 0.27398rem 0.770569rem; background: rgb(242, 242, 242);"></td><td aria-hidden="true" style="padding: 0.27398rem 0.770569rem; background: rgb(242, 242, 242);"></td><td aria-hidden="true" style="padding: 0.27398rem 0.770569rem; background: rgb(242, 242, 242);"></td><td aria-hidden="true" style="padding: 0.27398rem 0.770569rem; background: rgb(242, 242, 242);"></td><td aria-hidden="true" style="padding: 0.27398rem 0.770569rem; background: rgb(242, 242, 242);"></td><td aria-hidden="true" style="padding: 0.27398rem 0.770569rem; background: rgb(242, 242, 242);"></td><td aria-hidden="true" style="padding: 0.27398rem 0.770569rem; background: rgb(242, 242, 242); border-left: 1px solid rgba(0, 0, 0, 0.12);"></td><td aria-hidden="true" style="padding: 0.27398rem 0.770569rem; background: rgb(242, 242, 242);"></td><td aria-hidden="true" style="padding: 0.27398rem 0.770569rem; background: rgb(242, 242, 242);"></td></tr><tr><td style="padding: 0.470903rem 0.68495rem; text-align: left; vertical-align: middle; max-width: 188.361px; border-bottom: 1px solid rgba(0, 0, 0, 0.12);"><span style="display: block; line-height: 1.22; white-space: nowrap;">SWEBench Verified</span><span style="display: block; font-size: 0.88em; line-height: 1.25; color: rgb(107, 107, 107); margin-top: 0.18rem; white-space: normal;">Score</span></td><td style="padding: 0.470903rem 0.770569rem; text-align: center; vertical-align: middle; font-variant-numeric: tabular-nums; font-weight: 500; border-bottom: 1px solid rgba(0, 0, 0, 0.12); border-left: 1.5px solid rgba(0, 0, 0, 0.16); border-right: 1.5px solid rgba(0, 0, 0, 0.16);">80.2%</td><td style="padding: 0.470903rem 0.770569rem; text-align: center; vertical-align: middle; font-variant-numeric: tabular-nums; font-weight: 400; border-bottom: 1px solid rgba(0, 0, 0, 0.12);">76.4%</td><td style="padding: 0.470903rem 0.770569rem; text-align: center; vertical-align: middle; font-variant-numeric: tabular-nums; font-weight: 400; border-bottom: 1px solid rgba(0, 0, 0, 0.12);">71.0%</td><td style="padding: 0.470903rem 0.770569rem; text-align: center; vertical-align: middle; font-variant-numeric: tabular-nums; font-weight: 400; border-bottom: 1px solid rgba(0, 0, 0, 0.12);">79.9%</td><td style="padding: 0.470903rem 0.770569rem; text-align: center; vertical-align: middle; font-variant-numeric: tabular-nums; font-weight: 400; border-bottom: 1px solid rgba(0, 0, 0, 0.12);">79.0%</td><td style="padding: 0.470903rem 0.770569rem; text-align: center; vertical-align: middle; font-variant-numeric: tabular-nums; font-weight: 400; border-bottom: 1px solid rgba(0, 0, 0, 0.12);">70.7%</td><td style="padding: 0.470903rem 0.770569rem; text-align: center; vertical-align: middle; font-variant-numeric: tabular-nums; font-weight: 400; border-bottom: 1px solid rgba(0, 0, 0, 0.12);">77.6%</td><td style="padding: 0.470903rem 0.770569rem; text-align: center; vertical-align: middle; font-variant-numeric: tabular-nums; font-weight: 400; border-bottom: 1px solid rgba(0, 0, 0, 0.12); border-left: 1px solid rgba(0, 0, 0, 0.12);">66.6%</td><td style="padding: 0.470903rem 0.770569rem; text-align: center; vertical-align: middle; font-variant-numeric: tabular-nums; font-weight: 400; border-bottom: 1px solid rgba(0, 0, 0, 0.12);">75.0%</td><td style="padding: 0.470903rem 0.770569rem; text-align: center; vertical-align: middle; font-variant-numeric: tabular-nums; font-weight: 500; background: rgb(251, 236, 191); border-bottom: 1px solid rgba(0, 0, 0, 0.12);">93.0%</td></tr><tr><td style="padding: 0.470903rem 0.68495rem; text-align: left; vertical-align: middle; max-width: 188.361px; border-bottom: 1px solid rgba(0, 0, 0, 0.12);"><span style="display: block; line-height: 1.22; white-space: nowrap;">SWEBench Pro (Public)</span><span style="display: block; font-size: 0.88em; line-height: 1.25; color: rgb(107, 107, 107); margin-top: 0.18rem; white-space: normal;">Score</span></td><td style="padding: 0.470903rem 0.770569rem; text-align: center; vertical-align: middle; font-variant-numeric: tabular-nums; font-weight: 500; border-bottom: 1px solid rgba(0, 0, 0, 0.12); border-left: 1.5px solid rgba(0, 0, 0, 0.16); border-right: 1.5px solid rgba(0, 0, 0, 0.16);">55.9%</td><td style="padding: 0.470903rem 0.770569rem; text-align: center; vertical-align: middle; font-variant-numeric: tabular-nums; font-weight: 400; border-bottom: 1px solid rgba(0, 0, 0, 0.12);">50.9%</td><td style="padding: 0.470903rem 0.770569rem; text-align: center; vertical-align: middle; font-variant-numeric: tabular-nums; font-weight: 400; border-bottom: 1px solid rgba(0, 0, 0, 0.12);">56.1%</td><td style="padding: 0.470903rem 0.770569rem; text-align: center; vertical-align: middle; font-variant-numeric: tabular-nums; font-weight: 400; border-bottom: 1px solid rgba(0, 0, 0, 0.12);">56.2%</td><td style="padding: 0.470903rem 0.770569rem; text-align: center; vertical-align: middle; font-variant-numeric: tabular-nums; font-weight: 400; border-bottom: 1px solid rgba(0, 0, 0, 0.12);">52.6%</td><td style="padding: 0.470903rem 0.770569rem; text-align: center; vertical-align: middle; font-variant-numeric: tabular-nums; font-weight: 400; border-bottom: 1px solid rgba(0, 0, 0, 0.12);">46.4%</td><td style="padding: 0.470903rem 0.770569rem; text-align: center; vertical-align: middle; font-variant-numeric: tabular-nums; font-weight: 400; border-bottom: 1px solid rgba(0, 0, 0, 0.12);">54.3%</td><td style="padding: 0.470903rem 0.770569rem; text-align: center; vertical-align: middle; font-variant-numeric: tabular-nums; font-weight: 400; border-bottom: 1px solid rgba(0, 0, 0, 0.12); border-left: 1px solid rgba(0, 0, 0, 0.12);">39.5%</td><td style="padding: 0.470903rem 0.770569rem; text-align: center; vertical-align: middle; font-variant-numeric: tabular-nums; font-weight: 400; border-bottom: 1px solid rgba(0, 0, 0, 0.12);">54.2%</td><td style="padding: 0.470903rem 0.770569rem; text-align: center; vertical-align: middle; font-variant-numeric: tabular-nums; font-weight: 500; background: rgb(251, 236, 191); border-bottom: 1px solid rgba(0, 0, 0, 0.12);">62.7%</td></tr><tr><td style="padding: 0.470903rem 0.68495rem; text-align: left; vertical-align: middle; max-width: 188.361px; border-bottom: 1px solid rgba(0, 0, 0, 0.12);"><span style="display: block; line-height: 1.22; white-space: nowrap;">Terminal Bench 2.1</span><span style="display: block; font-size: 0.88em; line-height: 1.25; color: rgb(107, 107, 107); margin-top: 0.18rem; white-space: normal;">Best Harness</span></td><td style="padding: 0.470903rem 0.770569rem; text-align: center; vertical-align: middle; font-variant-numeric: tabular-nums; font-weight: 500; border-bottom: 1px solid rgba(0, 0, 0, 0.12); border-left: 1.5px solid rgba(0, 0, 0, 0.16); border-right: 1.5px solid rgba(0, 0, 0, 0.16);">64.69</td><td style="padding: 0.470903rem 0.770569rem; text-align: center; vertical-align: middle; font-variant-numeric: tabular-nums; font-weight: 400; border-bottom: 1px solid rgba(0, 0, 0, 0.12);">51.3</td><td style="padding: 0.470903rem 0.770569rem; text-align: center; vertical-align: middle; font-variant-numeric: tabular-nums; font-weight: 400; border-bottom: 1px solid rgba(0, 0, 0, 0.12);">63.7</td><td style="padding: 0.470903rem 0.770569rem; text-align: center; vertical-align: middle; font-variant-numeric: tabular-nums; font-weight: 400; border-bottom: 1px solid rgba(0, 0, 0, 0.12);">55.4</td><td style="padding: 0.470903rem 0.770569rem; text-align: center; vertical-align: middle; font-variant-numeric: tabular-nums; font-weight: 400; border-bottom: 1px solid rgba(0, 0, 0, 0.12);">61.8</td><td style="padding: 0.470903rem 0.770569rem; text-align: center; vertical-align: middle; font-variant-numeric: tabular-nums; font-weight: 400; border-bottom: 1px solid rgba(0, 0, 0, 0.12);">56.4</td><td style="padding: 0.470903rem 0.770569rem; text-align: center; vertical-align: middle; font-variant-numeric: tabular-nums; font-weight: 400; border-bottom: 1px solid rgba(0, 0, 0, 0.12);">63.8</td><td style="padding: 0.470903rem 0.770569rem; text-align: center; vertical-align: middle; font-variant-numeric: tabular-nums; font-weight: 400; border-bottom: 1px solid rgba(0, 0, 0, 0.12); border-left: 1px solid rgba(0, 0, 0, 0.12);">44.2</td><td style="padding: 0.470903rem 0.770569rem; text-align: center; vertical-align: middle; font-variant-numeric: tabular-nums; font-weight: 400; border-bottom: 1px solid rgba(0, 0, 0, 0.12);">54</td><td style="padding: 0.470903rem 0.770569rem; text-align: center; vertical-align: middle; font-variant-numeric: tabular-nums; font-weight: 500; background: rgb(251, 236, 191); border-bottom: 1px solid rgba(0, 0, 0, 0.12);">82.5</td></tr><tr><td style="padding: 0.470903rem 0.68495rem; text-align: left; vertical-align: middle; max-width: 188.361px; border-bottom: 1px solid rgba(0, 0, 0, 0.12);"><span style="display: block; line-height: 1.22; white-space: nowrap;">SciCode</span><span style="display: block; font-size: 0.88em; line-height: 1.25; color: rgb(107, 107, 107); margin-top: 0.18rem; white-space: normal;">Score</span></td><td style="padding: 0.470903rem 0.770569rem; text-align: center; vertical-align: middle; font-variant-numeric: tabular-nums; font-weight: 500; border-bottom: 1px solid rgba(0, 0, 0, 0.12); border-left: 1.5px solid rgba(0, 0, 0, 0.16); border-right: 1.5px solid rgba(0, 0, 0, 0.16);">48.7%</td><td style="padding: 0.470903rem 0.770569rem; text-align: center; vertical-align: middle; font-variant-numeric: tabular-nums; font-weight: 400; border-bottom: 1px solid rgba(0, 0, 0, 0.12);">42.0%</td><td style="padding: 0.470903rem 0.770569rem; text-align: center; vertical-align: middle; font-variant-numeric: tabular-nums; font-weight: 400; border-bottom: 1px solid rgba(0, 0, 0, 0.12);">43.1%</td><td style="padding: 0.470903rem 0.770569rem; text-align: center; vertical-align: middle; font-variant-numeric: tabular-nums; font-weight: 400; border-bottom: 1px solid rgba(0, 0, 0, 0.12);">47.0%</td><td style="padding: 0.470903rem 0.770569rem; text-align: center; vertical-align: middle; font-variant-numeric: tabular-nums; font-weight: 400; border-bottom: 1px solid rgba(0, 0, 0, 0.12);">44.9%</td><td style="padding: 0.470903rem 0.770569rem; text-align: center; vertical-align: middle; font-variant-numeric: tabular-nums; font-weight: 400; border-bottom: 1px solid rgba(0, 0, 0, 0.12);">39.9%</td><td style="padding: 0.470903rem 0.770569rem; text-align: center; vertical-align: middle; font-variant-numeric: tabular-nums; font-weight: 400; border-bottom: 1px solid rgba(0, 0, 0, 0.12);">46.1%</td><td style="padding: 0.470903rem 0.770569rem; text-align: center; vertical-align: middle; font-variant-numeric: tabular-nums; font-weight: 400; border-bottom: 1px solid rgba(0, 0, 0, 0.12); border-left: 1px solid rgba(0, 0, 0, 0.12);">43.3%</td><td style="padding: 0.470903rem 0.770569rem; text-align: center; vertical-align: middle; font-variant-numeric: tabular-nums; font-weight: 400; border-bottom: 1px solid rgba(0, 0, 0, 0.12);">40.9%</td><td style="padding: 0.470903rem 0.770569rem; text-align: center; vertical-align: middle; font-variant-numeric: tabular-nums; font-weight: 500; background: rgb(251, 236, 191); border-bottom: 1px solid rgba(0, 0, 0, 0.12);">50.0%</td></tr><tr><th scope="row" style="padding: 0.27398rem 0.68495rem; text-align: left; font-size: 0.92em; font-weight: 400; line-height: 1.2; color: rgb(107, 107, 107); background: rgb(242, 242, 242); white-space: nowrap;">Agentic (general)</th><td aria-hidden="true" style="padding: 0.27398rem 0.770569rem; background: rgb(242, 242, 242); border-left: 1.5px solid rgba(0, 0, 0, 0.16); border-right: 1.5px solid rgba(0, 0, 0, 0.16);"></td><td aria-hidden="true" style="padding: 0.27398rem 0.770569rem; background: rgb(242, 242, 242);"></td><td aria-hidden="true" style="padding: 0.27398rem 0.770569rem; background: rgb(242, 242, 242);"></td><td aria-hidden="true" style="padding: 0.27398rem 0.770569rem; background: rgb(242, 242, 242);"></td><td aria-hidden="true" style="padding: 0.27398rem 0.770569rem; background: rgb(242, 242, 242);"></td><td aria-hidden="true" style="padding: 0.27398rem 0.770569rem; background: rgb(242, 242, 242);"></td><td aria-hidden="true" style="padding: 0.27398rem 0.770569rem; background: rgb(242, 242, 242);"></td><td aria-hidden="true" style="padding: 0.27398rem 0.770569rem; background: rgb(242, 242, 242); border-left: 1px solid rgba(0, 0, 0, 0.12);"></td><td aria-hidden="true" style="padding: 0.27398rem 0.770569rem; background: rgb(242, 242, 242);"></td><td aria-hidden="true" style="padding: 0.27398rem 0.770569rem; background: rgb(242, 242, 242);"></td></tr><tr><td style="padding: 0.470903rem 0.68495rem; text-align: left; vertical-align: middle; max-width: 188.361px; border-bottom: 1px solid rgba(0, 0, 0, 0.12);"><span style="display: block; line-height: 1.22; white-space: nowrap;">GDPVal-AA v2</span><span style="display: block; font-size: 0.88em; line-height: 1.25; color: rgb(107, 107, 107); margin-top: 0.18rem; white-space: normal;">Score</span></td><td style="padding: 0.470903rem 0.770569rem; text-align: center; vertical-align: middle; font-variant-numeric: tabular-nums; font-weight: 500; border-bottom: 1px solid rgba(0, 0, 0, 0.12); border-left: 1.5px solid rgba(0, 0, 0, 0.16); border-right: 1.5px solid rgba(0, 0, 0, 0.16);">1269</td><td style="padding: 0.470903rem 0.770569rem; text-align: center; vertical-align: middle; font-variant-numeric: tabular-nums; font-weight: 400; border-bottom: 1px solid rgba(0, 0, 0, 0.12);">962</td><td style="padding: 0.470903rem 0.770569rem; text-align: center; vertical-align: middle; font-variant-numeric: tabular-nums; font-weight: 400; border-bottom: 1px solid rgba(0, 0, 0, 0.12);">1145</td><td style="padding: 0.470903rem 0.770569rem; text-align: center; vertical-align: middle; font-variant-numeric: tabular-nums; font-weight: 400; border-bottom: 1px solid rgba(0, 0, 0, 0.12);">1159</td><td style="padding: 0.470903rem 0.770569rem; text-align: center; vertical-align: middle; font-variant-numeric: tabular-nums; font-weight: 400; border-bottom: 1px solid rgba(0, 0, 0, 0.12);">1189</td><td style="padding: 0.470903rem 0.770569rem; text-align: center; vertical-align: middle; font-variant-numeric: tabular-nums; font-weight: 400; border-bottom: 1px solid rgba(0, 0, 0, 0.12);">1164</td><td style="padding: 0.470903rem 0.770569rem; text-align: center; vertical-align: middle; font-variant-numeric: tabular-nums; font-weight: 400; border-bottom: 1px solid rgba(0, 0, 0, 0.12);">1238</td><td style="padding: 0.470903rem 0.770569rem; text-align: center; vertical-align: middle; font-variant-numeric: tabular-nums; font-weight: 400; border-bottom: 1px solid rgba(0, 0, 0, 0.12); border-left: 1px solid rgba(0, 0, 0, 0.12);">911</td><td style="padding: 0.470903rem 0.770569rem; text-align: center; vertical-align: middle; font-variant-numeric: tabular-nums; font-weight: 400; border-bottom: 1px solid rgba(0, 0, 0, 0.12);">1139</td><td style="padding: 0.470903rem 0.770569rem; text-align: center; vertical-align: middle; font-variant-numeric: tabular-nums; font-weight: 500; background: rgb(251, 236, 191); border-bottom: 1px solid rgba(0, 0, 0, 0.12);">1530</td></tr><tr><td style="padding: 0.470903rem 0.68495rem; text-align: left; vertical-align: middle; max-width: 188.361px; border-bottom: 1px solid rgba(0, 0, 0, 0.12);"><span style="display: block; line-height: 1.22; white-space: nowrap;">MCP Atlas</span><span style="display: block; font-size: 0.88em; line-height: 1.25; color: rgb(107, 107, 107); margin-top: 0.18rem; white-space: normal;">Public</span></td><td style="padding: 0.470903rem 0.770569rem; text-align: center; vertical-align: middle; font-variant-numeric: tabular-nums; font-weight: 500; border-bottom: 1px solid rgba(0, 0, 0, 0.12); border-left: 1.5px solid rgba(0, 0, 0, 0.16); border-right: 1.5px solid rgba(0, 0, 0, 0.16);">79.6</td><td style="padding: 0.470903rem 0.770569rem; text-align: center; vertical-align: middle; font-variant-numeric: tabular-nums; font-weight: 400; border-bottom: 1px solid rgba(0, 0, 0, 0.12);">74.2</td><td style="padding: 0.470903rem 0.770569rem; text-align: center; vertical-align: middle; font-variant-numeric: tabular-nums; font-weight: 400; border-bottom: 1px solid rgba(0, 0, 0, 0.12);">–</td><td style="padding: 0.470903rem 0.770569rem; text-align: center; vertical-align: middle; font-variant-numeric: tabular-nums; font-weight: 400; border-bottom: 1px solid rgba(0, 0, 0, 0.12);">49.4</td><td style="padding: 0.470903rem 0.770569rem; text-align: center; vertical-align: middle; font-variant-numeric: tabular-nums; font-weight: 400; border-bottom: 1px solid rgba(0, 0, 0, 0.12);">69</td><td style="padding: 0.470903rem 0.770569rem; text-align: center; vertical-align: middle; font-variant-numeric: tabular-nums; font-weight: 400; border-bottom: 1px solid rgba(0, 0, 0, 0.12);">47.4</td><td style="padding: 0.470903rem 0.770569rem; text-align: center; vertical-align: middle; font-variant-numeric: tabular-nums; font-weight: 400; border-bottom: 1px solid rgba(0, 0, 0, 0.12);">78.8</td><td style="padding: 0.470903rem 0.770569rem; text-align: center; vertical-align: middle; font-variant-numeric: tabular-nums; font-weight: 400; border-bottom: 1px solid rgba(0, 0, 0, 0.12); border-left: 1px solid rgba(0, 0, 0, 0.12);">41.2</td><td style="padding: 0.470903rem 0.770569rem; text-align: center; vertical-align: middle; font-variant-numeric: tabular-nums; font-weight: 500; background: rgb(251, 236, 191); border-bottom: 1px solid rgba(0, 0, 0, 0.12);">79.8</td><td style="padding: 0.470903rem 0.770569rem; text-align: center; vertical-align: middle; font-variant-numeric: tabular-nums; font-weight: 400; border-bottom: 1px solid rgba(0, 0, 0, 0.12);">77</td></tr><tr><td style="padding: 0.470903rem 0.68495rem; text-align: left; vertical-align: middle; max-width: 188.361px; border-bottom: 1px solid rgba(0, 0, 0, 0.12);"><span style="display: block; line-height: 1.22; white-space: nowrap;">MCP Atlas</span><span style="display: block; font-size: 0.88em; line-height: 1.25; color: rgb(107, 107, 107); margin-top: 0.18rem; white-space: normal;">All</span></td><td style="padding: 0.470903rem 0.770569rem; text-align: center; vertical-align: middle; font-variant-numeric: tabular-nums; font-weight: 500; background: rgb(251, 236, 191); border-bottom: 1px solid rgba(0, 0, 0, 0.12); border-left: 1.5px solid rgba(0, 0, 0, 0.16); border-right: 1.5px solid rgba(0, 0, 0, 0.16);">79.2</td><td style="padding: 0.470903rem 0.770569rem; text-align: center; vertical-align: middle; font-variant-numeric: tabular-nums; font-weight: 400; border-bottom: 1px solid rgba(0, 0, 0, 0.12);">–</td><td style="padding: 0.470903rem 0.770569rem; text-align: center; vertical-align: middle; font-variant-numeric: tabular-nums; font-weight: 400; border-bottom: 1px solid rgba(0, 0, 0, 0.12);">–</td><td style="padding: 0.470903rem 0.770569rem; text-align: center; vertical-align: middle; font-variant-numeric: tabular-nums; font-weight: 400; border-bottom: 1px solid rgba(0, 0, 0, 0.12);">–</td><td style="padding: 0.470903rem 0.770569rem; text-align: center; vertical-align: middle; font-variant-numeric: tabular-nums; font-weight: 400; border-bottom: 1px solid rgba(0, 0, 0, 0.12);">–</td><td style="padding: 0.470903rem 0.770569rem; text-align: center; vertical-align: middle; font-variant-numeric: tabular-nums; font-weight: 400; border-bottom: 1px solid rgba(0, 0, 0, 0.12);">44.7</td><td style="padding: 0.470903rem 0.770569rem; text-align: center; vertical-align: middle; font-variant-numeric: tabular-nums; font-weight: 400; border-bottom: 1px solid rgba(0, 0, 0, 0.12);">76</td><td style="padding: 0.470903rem 0.770569rem; text-align: center; vertical-align: middle; font-variant-numeric: tabular-nums; font-weight: 400; border-bottom: 1px solid rgba(0, 0, 0, 0.12); border-left: 1px solid rgba(0, 0, 0, 0.12);">40.2</td><td style="padding: 0.470903rem 0.770569rem; text-align: center; vertical-align: middle; font-variant-numeric: tabular-nums; font-weight: 400; border-bottom: 1px solid rgba(0, 0, 0, 0.12);">76.8</td><td style="padding: 0.470903rem 0.770569rem; text-align: center; vertical-align: middle; font-variant-numeric: tabular-nums; font-weight: 400; border-bottom: 1px solid rgba(0, 0, 0, 0.12);">75</td></tr><tr><td style="padding: 0.470903rem 0.68495rem; text-align: left; vertical-align: middle; max-width: 188.361px; border-bottom: 1px solid rgba(0, 0, 0, 0.12);"><span style="display: block; line-height: 1.22; white-space: nowrap;">Tau 3 Banking</span><span style="display: block; font-size: 0.88em; line-height: 1.25; color: rgb(107, 107, 107); margin-top: 0.18rem; white-space: normal;">Score</span></td><td style="padding: 0.470903rem 0.770569rem; text-align: center; vertical-align: middle; font-variant-numeric: tabular-nums; font-weight: 500; border-bottom: 1px solid rgba(0, 0, 0, 0.12); border-left: 1.5px solid rgba(0, 0, 0, 0.16); border-right: 1.5px solid rgba(0, 0, 0, 0.16);">15.5%</td><td style="padding: 0.470903rem 0.770569rem; text-align: center; vertical-align: middle; font-variant-numeric: tabular-nums; font-weight: 400; border-bottom: 1px solid rgba(0, 0, 0, 0.12);">13.4%</td><td style="padding: 0.470903rem 0.770569rem; text-align: center; vertical-align: middle; font-variant-numeric: tabular-nums; font-weight: 400; border-bottom: 1px solid rgba(0, 0, 0, 0.12);">6.6%</td><td style="padding: 0.470903rem 0.770569rem; text-align: center; vertical-align: middle; font-variant-numeric: tabular-nums; font-weight: 400; border-bottom: 1px solid rgba(0, 0, 0, 0.12);">8.9%</td><td style="padding: 0.470903rem 0.770569rem; text-align: center; vertical-align: middle; font-variant-numeric: tabular-nums; font-weight: 400; border-bottom: 1px solid rgba(0, 0, 0, 0.12);">22.9%</td><td style="padding: 0.470903rem 0.770569rem; text-align: center; vertical-align: middle; font-variant-numeric: tabular-nums; font-weight: 400; border-bottom: 1px solid rgba(0, 0, 0, 0.12);">13.8%</td><td style="padding: 0.470903rem 0.770569rem; text-align: center; vertical-align: middle; font-variant-numeric: tabular-nums; font-weight: 400; border-bottom: 1px solid rgba(0, 0, 0, 0.12);">23.7%</td><td style="padding: 0.470903rem 0.770569rem; text-align: center; vertical-align: middle; font-variant-numeric: tabular-nums; font-weight: 400; border-bottom: 1px solid rgba(0, 0, 0, 0.12); border-left: 1px solid rgba(0, 0, 0, 0.12);">9.1%</td><td style="padding: 0.470903rem 0.770569rem; text-align: center; vertical-align: middle; font-variant-numeric: tabular-nums; font-weight: 400; border-bottom: 1px solid rgba(0, 0, 0, 0.12);">16.5%</td><td style="padding: 0.470903rem 0.770569rem; text-align: center; vertical-align: middle; font-variant-numeric: tabular-nums; font-weight: 500; background: rgb(251, 236, 191); border-bottom: 1px solid rgba(0, 0, 0, 0.12);">24.3%</td></tr><tr><td style="padding: 0.470903rem 0.68495rem; text-align: left; vertical-align: middle; max-width: 188.361px; border-bottom: 1px solid rgba(0, 0, 0, 0.12);"><span style="display: block; line-height: 1.22; white-space: nowrap;">BrowseComp (w/ Ctx)</span><span style="display: block; font-size: 0.88em; line-height: 1.25; color: rgb(107, 107, 107); margin-top: 0.18rem; white-space: normal;">Score</span></td><td style="padding: 0.470903rem 0.770569rem; text-align: center; vertical-align: middle; font-variant-numeric: tabular-nums; font-weight: 500; border-bottom: 1px solid rgba(0, 0, 0, 0.12); border-left: 1.5px solid rgba(0, 0, 0, 0.16); border-right: 1.5px solid rgba(0, 0, 0, 0.16);">77.4%</td><td style="padding: 0.470903rem 0.770569rem; text-align: center; vertical-align: middle; font-variant-numeric: tabular-nums; font-weight: 400; border-bottom: 1px solid rgba(0, 0, 0, 0.12);">78.6%</td><td style="padding: 0.470903rem 0.770569rem; text-align: center; vertical-align: middle; font-variant-numeric: tabular-nums; font-weight: 400; border-bottom: 1px solid rgba(0, 0, 0, 0.12);">–</td><td style="padding: 0.470903rem 0.770569rem; text-align: center; vertical-align: middle; font-variant-numeric: tabular-nums; font-weight: 400; border-bottom: 1px solid rgba(0, 0, 0, 0.12);">76.3%</td><td style="padding: 0.470903rem 0.770569rem; text-align: center; vertical-align: middle; font-variant-numeric: tabular-nums; font-weight: 400; border-bottom: 1px solid rgba(0, 0, 0, 0.12);">73.2%</td><td style="padding: 0.470903rem 0.770569rem; text-align: center; vertical-align: middle; font-variant-numeric: tabular-nums; font-weight: 400; border-bottom: 1px solid rgba(0, 0, 0, 0.12);">63.0%</td><td style="padding: 0.470903rem 0.770569rem; text-align: center; vertical-align: middle; font-variant-numeric: tabular-nums; font-weight: 400; border-bottom: 1px solid rgba(0, 0, 0, 0.12);">77.1%</td><td style="padding: 0.470903rem 0.770569rem; text-align: center; vertical-align: middle; font-variant-numeric: tabular-nums; font-weight: 400; border-bottom: 1px solid rgba(0, 0, 0, 0.12); border-left: 1px solid rgba(0, 0, 0, 0.12);">–</td><td style="padding: 0.470903rem 0.770569rem; text-align: center; vertical-align: middle; font-variant-numeric: tabular-nums; font-weight: 400; border-bottom: 1px solid rgba(0, 0, 0, 0.12);">–</td><td style="padding: 0.470903rem 0.770569rem; text-align: center; vertical-align: middle; font-variant-numeric: tabular-nums; font-weight: 500; background: rgb(251, 236, 191); border-bottom: 1px solid rgba(0, 0, 0, 0.12);">84.0%</td></tr><tr><td style="padding: 0.470903rem 0.68495rem; text-align: left; vertical-align: middle; max-width: 188.361px; border-bottom: 1px solid rgba(0, 0, 0, 0.12);"><span style="display: block; line-height: 1.22; white-space: nowrap;">Toolathlon-Verified</span><span style="display: block; font-size: 0.88em; line-height: 1.25; color: rgb(107, 107, 107); margin-top: 0.18rem; white-space: normal;">Score</span></td><td style="padding: 0.470903rem 0.770569rem; text-align: center; vertical-align: middle; font-variant-numeric: tabular-nums; font-weight: 500; background: rgb(251, 236, 191); border-bottom: 1px solid rgba(0, 0, 0, 0.12); border-left: 1.5px solid rgba(0, 0, 0, 0.16); border-right: 1.5px solid rgba(0, 0, 0, 0.16);">54.4%</td><td style="padding: 0.470903rem 0.770569rem; text-align: center; vertical-align: middle; font-variant-numeric: tabular-nums; font-weight: 400; border-bottom: 1px solid rgba(0, 0, 0, 0.12);">–</td><td style="padding: 0.470903rem 0.770569rem; text-align: center; vertical-align: middle; font-variant-numeric: tabular-nums; font-weight: 400; border-bottom: 1px solid rgba(0, 0, 0, 0.12);">–</td><td style="padding: 0.470903rem 0.770569rem; text-align: center; vertical-align: middle; font-variant-numeric: tabular-nums; font-weight: 400; border-bottom: 1px solid rgba(0, 0, 0, 0.12);">–</td><td style="padding: 0.470903rem 0.770569rem; text-align: center; vertical-align: middle; font-variant-numeric: tabular-nums; font-weight: 400; border-bottom: 1px solid rgba(0, 0, 0, 0.12);">–</td><td style="padding: 0.470903rem 0.770569rem; text-align: center; vertical-align: middle; font-variant-numeric: tabular-nums; font-weight: 400; border-bottom: 1px solid rgba(0, 0, 0, 0.12);">34.3%</td><td style="padding: 0.470903rem 0.770569rem; text-align: center; vertical-align: middle; font-variant-numeric: tabular-nums; font-weight: 400; border-bottom: 1px solid rgba(0, 0, 0, 0.12);">45.5%</td><td style="padding: 0.470903rem 0.770569rem; text-align: center; vertical-align: middle; font-variant-numeric: tabular-nums; font-weight: 400; border-bottom: 1px solid rgba(0, 0, 0, 0.12); border-left: 1px solid rgba(0, 0, 0, 0.12);">–</td><td style="padding: 0.470903rem 0.770569rem; text-align: center; vertical-align: middle; font-variant-numeric: tabular-nums; font-weight: 400; border-bottom: 1px solid rgba(0, 0, 0, 0.12);">–</td><td style="padding: 0.470903rem 0.770569rem; text-align: center; vertical-align: middle; font-variant-numeric: tabular-nums; font-weight: 400; border-bottom: 1px solid rgba(0, 0, 0, 0.12);">–</td></tr><tr><td style="padding: 0.470903rem 0.68495rem; text-align: left; vertical-align: middle; max-width: 188.361px; border-bottom: 1px solid rgba(0, 0, 0, 0.12);"><span style="display: block; line-height: 1.22; white-space: nowrap;">AA-Briefcase</span><span style="display: block; font-size: 0.88em; line-height: 1.25; color: rgb(107, 107, 107); margin-top: 0.18rem; white-space: normal;">Score</span></td><td style="padding: 0.470903rem 0.770569rem; text-align: center; vertical-align: middle; font-variant-numeric: tabular-nums; font-weight: 500; background: rgb(251, 236, 191); border-bottom: 1px solid rgba(0, 0, 0, 0.12); border-left: 1.5px solid rgba(0, 0, 0, 0.16); border-right: 1.5px solid rgba(0, 0, 0, 0.16);">917</td><td style="padding: 0.470903rem 0.770569rem; text-align: center; vertical-align: middle; font-variant-numeric: tabular-nums; font-weight: 400; border-bottom: 1px solid rgba(0, 0, 0, 0.12);">–</td><td style="padding: 0.470903rem 0.770569rem; text-align: center; vertical-align: middle; font-variant-numeric: tabular-nums; font-weight: 400; border-bottom: 1px solid rgba(0, 0, 0, 0.12);">–</td><td style="padding: 0.470903rem 0.770569rem; text-align: center; vertical-align: middle; font-variant-numeric: tabular-nums; font-weight: 400; border-bottom: 1px solid rgba(0, 0, 0, 0.12);">–</td><td style="padding: 0.470903rem 0.770569rem; text-align: center; vertical-align: middle; font-variant-numeric: tabular-nums; font-weight: 400; border-bottom: 1px solid rgba(0, 0, 0, 0.12);">833</td><td style="padding: 0.470903rem 0.770569rem; text-align: center; vertical-align: middle; font-variant-numeric: tabular-nums; font-weight: 400; border-bottom: 1px solid rgba(0, 0, 0, 0.12);">870</td><td style="padding: 0.470903rem 0.770569rem; text-align: center; vertical-align: middle; font-variant-numeric: tabular-nums; font-weight: 400; border-bottom: 1px solid rgba(0, 0, 0, 0.12);">839</td><td style="padding: 0.470903rem 0.770569rem; text-align: center; vertical-align: middle; font-variant-numeric: tabular-nums; font-weight: 400; border-bottom: 1px solid rgba(0, 0, 0, 0.12); border-left: 1px solid rgba(0, 0, 0, 0.12);">612</td><td style="padding: 0.470903rem 0.770569rem; text-align: center; vertical-align: middle; font-variant-numeric: tabular-nums; font-weight: 400; border-bottom: 1px solid rgba(0, 0, 0, 0.12);">–</td><td style="padding: 0.470903rem 0.770569rem; text-align: center; vertical-align: middle; font-variant-numeric: tabular-nums; font-weight: 400; border-bottom: 1px solid rgba(0, 0, 0, 0.12);">–</td></tr><tr><th scope="row" style="padding: 0.27398rem 0.68495rem; text-align: left; font-size: 0.92em; font-weight: 400; line-height: 1.2; color: rgb(107, 107, 107); background: rgb(242, 242, 242); white-space: nowrap;">Reasoning (general)</th><td aria-hidden="true" style="padding: 0.27398rem 0.770569rem; background: rgb(242, 242, 242); border-left: 1.5px solid rgba(0, 0, 0, 0.16); border-right: 1.5px solid rgba(0, 0, 0, 0.16);"></td><td aria-hidden="true" style="padding: 0.27398rem 0.770569rem; background: rgb(242, 242, 242);"></td><td aria-hidden="true" style="padding: 0.27398rem 0.770569rem; background: rgb(242, 242, 242);"></td><td aria-hidden="true" style="padding: 0.27398rem 0.770569rem; background: rgb(242, 242, 242);"></td><td aria-hidden="true" style="padding: 0.27398rem 0.770569rem; background: rgb(242, 242, 242);"></td><td aria-hidden="true" style="padding: 0.27398rem 0.770569rem; background: rgb(242, 242, 242);"></td><td aria-hidden="true" style="padding: 0.27398rem 0.770569rem; background: rgb(242, 242, 242);"></td><td aria-hidden="true" style="padding: 0.27398rem 0.770569rem; background: rgb(242, 242, 242); border-left: 1px solid rgba(0, 0, 0, 0.12);"></td><td aria-hidden="true" style="padding: 0.27398rem 0.770569rem; background: rgb(242, 242, 242);"></td><td aria-hidden="true" style="padding: 0.27398rem 0.770569rem; background: rgb(242, 242, 242);"></td></tr><tr><td style="padding: 0.470903rem 0.68495rem; text-align: left; vertical-align: middle; max-width: 188.361px; border-bottom: 1px solid rgba(0, 0, 0, 0.12);"><span style="display: block; line-height: 1.22; white-space: nowrap;">GPQA Diamond</span><span style="display: block; font-size: 0.88em; line-height: 1.25; color: rgb(107, 107, 107); margin-top: 0.18rem; white-space: normal;">Score</span></td><td style="padding: 0.470903rem 0.770569rem; text-align: center; vertical-align: middle; font-variant-numeric: tabular-nums; font-weight: 500; background: rgb(251, 236, 191); border-bottom: 1px solid rgba(0, 0, 0, 0.12); border-left: 1.5px solid rgba(0, 0, 0, 0.16); border-right: 1.5px solid rgba(0, 0, 0, 0.16);">89.5%</td><td style="padding: 0.470903rem 0.770569rem; text-align: center; vertical-align: middle; font-variant-numeric: tabular-nums; font-weight: 400; border-bottom: 1px solid rgba(0, 0, 0, 0.12);">89.3%</td><td style="padding: 0.470903rem 0.770569rem; text-align: center; vertical-align: middle; font-variant-numeric: tabular-nums; font-weight: 400; border-bottom: 1px solid rgba(0, 0, 0, 0.12);">84.9%</td><td style="padding: 0.470903rem 0.770569rem; text-align: center; vertical-align: middle; font-variant-numeric: tabular-nums; font-weight: 400; border-bottom: 1px solid rgba(0, 0, 0, 0.12);">87.4%</td><td style="padding: 0.470903rem 0.770569rem; text-align: center; vertical-align: middle; font-variant-numeric: tabular-nums; font-weight: 400; border-bottom: 1px solid rgba(0, 0, 0, 0.12);">89.4%</td><td style="padding: 0.470903rem 0.770569rem; text-align: center; vertical-align: middle; font-variant-numeric: tabular-nums; font-weight: 400; border-bottom: 1px solid rgba(0, 0, 0, 0.12);">86.7%</td><td style="padding: 0.470903rem 0.770569rem; text-align: center; vertical-align: middle; font-variant-numeric: tabular-nums; font-weight: 400; border-bottom: 1px solid rgba(0, 0, 0, 0.12);">87.2%</td><td style="padding: 0.470903rem 0.770569rem; text-align: center; vertical-align: middle; font-variant-numeric: tabular-nums; font-weight: 400; border-bottom: 1px solid rgba(0, 0, 0, 0.12); border-left: 1px solid rgba(0, 0, 0, 0.12);">67.2%</td><td style="padding: 0.470903rem 0.770569rem; text-align: center; vertical-align: middle; font-variant-numeric: tabular-nums; font-weight: 400; border-bottom: 1px solid rgba(0, 0, 0, 0.12);">83.8%</td><td style="padding: 0.470903rem 0.770569rem; text-align: center; vertical-align: middle; font-variant-numeric: tabular-nums; font-weight: 500; background: rgb(251, 236, 191); border-bottom: 1px solid rgba(0, 0, 0, 0.12);">89.5%</td></tr><tr><td style="padding: 0.470903rem 0.68495rem; text-align: left; vertical-align: middle; max-width: 188.361px; border-bottom: 1px solid rgba(0, 0, 0, 0.12);"><span style="display: block; line-height: 1.22; white-space: nowrap;">HLE (text only)</span><span style="display: block; font-size: 0.88em; line-height: 1.25; color: rgb(107, 107, 107); margin-top: 0.18rem; white-space: normal;">Score</span></td><td style="padding: 0.470903rem 0.770569rem; text-align: center; vertical-align: middle; font-variant-numeric: tabular-nums; font-weight: 500; border-bottom: 1px solid rgba(0, 0, 0, 0.12); border-left: 1.5px solid rgba(0, 0, 0, 0.16); border-right: 1.5px solid rgba(0, 0, 0, 0.16);">31.6%</td><td style="padding: 0.470903rem 0.770569rem; text-align: center; vertical-align: middle; font-variant-numeric: tabular-nums; font-weight: 400; border-bottom: 1px solid rgba(0, 0, 0, 0.12);">27.3%</td><td style="padding: 0.470903rem 0.770569rem; text-align: center; vertical-align: middle; font-variant-numeric: tabular-nums; font-weight: 400; border-bottom: 1px solid rgba(0, 0, 0, 0.12);">25.2%</td><td style="padding: 0.470903rem 0.770569rem; text-align: center; vertical-align: middle; font-variant-numeric: tabular-nums; font-weight: 400; border-bottom: 1px solid rgba(0, 0, 0, 0.12);">28.1%</td><td style="padding: 0.470903rem 0.770569rem; text-align: center; vertical-align: middle; font-variant-numeric: tabular-nums; font-weight: 400; border-bottom: 1px solid rgba(0, 0, 0, 0.12);">32.1%</td><td style="padding: 0.470903rem 0.770569rem; text-align: center; vertical-align: middle; font-variant-numeric: tabular-nums; font-weight: 400; border-bottom: 1px solid rgba(0, 0, 0, 0.12);">26.6%</td><td style="padding: 0.470903rem 0.770569rem; text-align: center; vertical-align: middle; font-variant-numeric: tabular-nums; font-weight: 400; border-bottom: 1px solid rgba(0, 0, 0, 0.12);">29.7%</td><td style="padding: 0.470903rem 0.770569rem; text-align: center; vertical-align: middle; font-variant-numeric: tabular-nums; font-weight: 400; border-bottom: 1px solid rgba(0, 0, 0, 0.12); border-left: 1px solid rgba(0, 0, 0, 0.12);">9.7%</td><td style="padding: 0.470903rem 0.770569rem; text-align: center; vertical-align: middle; font-variant-numeric: tabular-nums; font-weight: 400; border-bottom: 1px solid rgba(0, 0, 0, 0.12);">17.5%</td><td style="padding: 0.470903rem 0.770569rem; text-align: center; vertical-align: middle; font-variant-numeric: tabular-nums; font-weight: 500; background: rgb(251, 236, 191); border-bottom: 1px solid rgba(0, 0, 0, 0.12);">35.6%</td></tr><tr><td style="padding: 0.470903rem 0.68495rem; text-align: left; vertical-align: middle; max-width: 188.361px; border-bottom: 1px solid rgba(0, 0, 0, 0.12);"><span style="display: block; line-height: 1.22; white-space: nowrap;">HLE (with tools)</span><span style="display: block; font-size: 0.88em; line-height: 1.25; color: rgb(107, 107, 107); margin-top: 0.18rem; white-space: normal;">Score</span></td><td style="padding: 0.470903rem 0.770569rem; text-align: center; vertical-align: middle; font-variant-numeric: tabular-nums; font-weight: 500; border-bottom: 1px solid rgba(0, 0, 0, 0.12); border-left: 1.5px solid rgba(0, 0, 0, 0.16); border-right: 1.5px solid rgba(0, 0, 0, 0.16);">47.8%</td><td style="padding: 0.470903rem 0.770569rem; text-align: center; vertical-align: middle; font-variant-numeric: tabular-nums; font-weight: 400; border-bottom: 1px solid rgba(0, 0, 0, 0.12);">48.3%</td><td style="padding: 0.470903rem 0.770569rem; text-align: center; vertical-align: middle; font-variant-numeric: tabular-nums; font-weight: 400; border-bottom: 1px solid rgba(0, 0, 0, 0.12);">40.0%</td><td style="padding: 0.470903rem 0.770569rem; text-align: center; vertical-align: middle; font-variant-numeric: tabular-nums; font-weight: 400; border-bottom: 1px solid rgba(0, 0, 0, 0.12);">40.3%</td><td style="padding: 0.470903rem 0.770569rem; text-align: center; vertical-align: middle; font-variant-numeric: tabular-nums; font-weight: 400; border-bottom: 1px solid rgba(0, 0, 0, 0.12);">45.1%</td><td style="padding: 0.470903rem 0.770569rem; text-align: center; vertical-align: middle; font-variant-numeric: tabular-nums; font-weight: 400; border-bottom: 1px solid rgba(0, 0, 0, 0.12);">37.4%</td><td style="padding: 0.470903rem 0.770569rem; text-align: center; vertical-align: middle; font-variant-numeric: tabular-nums; font-weight: 400; border-bottom: 1px solid rgba(0, 0, 0, 0.12);">46.0%</td><td style="padding: 0.470903rem 0.770569rem; text-align: center; vertical-align: middle; font-variant-numeric: tabular-nums; font-weight: 400; border-bottom: 1px solid rgba(0, 0, 0, 0.12); border-left: 1px solid rgba(0, 0, 0, 0.12);">17.6%</td><td style="padding: 0.470903rem 0.770569rem; text-align: center; vertical-align: middle; font-variant-numeric: tabular-nums; font-weight: 400; border-bottom: 1px solid rgba(0, 0, 0, 0.12);">42.5%</td><td style="padding: 0.470903rem 0.770569rem; text-align: center; vertical-align: middle; font-variant-numeric: tabular-nums; font-weight: 500; background: rgb(251, 236, 191); border-bottom: 1px solid rgba(0, 0, 0, 0.12);">48.9%</td></tr><tr><td style="padding: 0.470903rem 0.68495rem; text-align: left; vertical-align: middle; max-width: 188.361px; border-bottom: 1px solid rgba(0, 0, 0, 0.12);"><span style="display: block; line-height: 1.22; white-space: nowrap;">AIME 2026</span><span style="display: block; font-size: 0.88em; line-height: 1.25; color: rgb(107, 107, 107); margin-top: 0.18rem; white-space: normal;">Score</span></td><td style="padding: 0.470903rem 0.770569rem; text-align: center; vertical-align: middle; font-variant-numeric: tabular-nums; font-weight: 500; border-bottom: 1px solid rgba(0, 0, 0, 0.12); border-left: 1.5px solid rgba(0, 0, 0, 0.16); border-right: 1.5px solid rgba(0, 0, 0, 0.16);">95.5%</td><td style="padding: 0.470903rem 0.770569rem; text-align: center; vertical-align: middle; font-variant-numeric: tabular-nums; font-weight: 400; border-bottom: 1px solid rgba(0, 0, 0, 0.12);">93.3%</td><td style="padding: 0.470903rem 0.770569rem; text-align: center; vertical-align: middle; font-variant-numeric: tabular-nums; font-weight: 400; border-bottom: 1px solid rgba(0, 0, 0, 0.12);">93.6%</td><td style="padding: 0.470903rem 0.770569rem; text-align: center; vertical-align: middle; font-variant-numeric: tabular-nums; font-weight: 400; border-bottom: 1px solid rgba(0, 0, 0, 0.12);">87.7%</td><td style="padding: 0.470903rem 0.770569rem; text-align: center; vertical-align: middle; font-variant-numeric: tabular-nums; font-weight: 400; border-bottom: 1px solid rgba(0, 0, 0, 0.12);">95.8%</td><td style="padding: 0.470903rem 0.770569rem; text-align: center; vertical-align: middle; font-variant-numeric: tabular-nums; font-weight: 400; border-bottom: 1px solid rgba(0, 0, 0, 0.12);">94.2%</td><td style="padding: 0.470903rem 0.770569rem; text-align: center; vertical-align: middle; font-variant-numeric: tabular-nums; font-weight: 400; border-bottom: 1px solid rgba(0, 0, 0, 0.12);">97.1%</td><td style="padding: 0.470903rem 0.770569rem; text-align: center; vertical-align: middle; font-variant-numeric: tabular-nums; font-weight: 400; border-bottom: 1px solid rgba(0, 0, 0, 0.12); border-left: 1px solid rgba(0, 0, 0, 0.12);">81.2%</td><td style="padding: 0.470903rem 0.770569rem; text-align: center; vertical-align: middle; font-variant-numeric: tabular-nums; font-weight: 400; border-bottom: 1px solid rgba(0, 0, 0, 0.12);">82.2%</td><td style="padding: 0.470903rem 0.770569rem; text-align: center; vertical-align: middle; font-variant-numeric: tabular-nums; font-weight: 500; background: rgb(251, 236, 191); border-bottom: 1px solid rgba(0, 0, 0, 0.12);">97.6%</td></tr><tr><td style="padding: 0.470903rem 0.68495rem; text-align: left; vertical-align: middle; max-width: 188.361px; border-bottom: 1px solid rgba(0, 0, 0, 0.12);"><span style="display: block; line-height: 1.22; white-space: nowrap;">HMMT Feb 2026</span><span style="display: block; font-size: 0.88em; line-height: 1.25; color: rgb(107, 107, 107); margin-top: 0.18rem; white-space: normal;">Score</span></td><td style="padding: 0.470903rem 0.770569rem; text-align: center; vertical-align: middle; font-variant-numeric: tabular-nums; font-weight: 500; border-bottom: 1px solid rgba(0, 0, 0, 0.12); border-left: 1.5px solid rgba(0, 0, 0, 0.16); border-right: 1.5px solid rgba(0, 0, 0, 0.16);">90.2%</td><td style="padding: 0.470903rem 0.770569rem; text-align: center; vertical-align: middle; font-variant-numeric: tabular-nums; font-weight: 400; border-bottom: 1px solid rgba(0, 0, 0, 0.12);">87.9%</td><td style="padding: 0.470903rem 0.770569rem; text-align: center; vertical-align: middle; font-variant-numeric: tabular-nums; font-weight: 400; border-bottom: 1px solid rgba(0, 0, 0, 0.12);">82.6%</td><td style="padding: 0.470903rem 0.770569rem; text-align: center; vertical-align: middle; font-variant-numeric: tabular-nums; font-weight: 400; border-bottom: 1px solid rgba(0, 0, 0, 0.12);">71.2%</td><td style="padding: 0.470903rem 0.770569rem; text-align: center; vertical-align: middle; font-variant-numeric: tabular-nums; font-weight: 400; border-bottom: 1px solid rgba(0, 0, 0, 0.12);">93.9%</td><td style="padding: 0.470903rem 0.770569rem; text-align: center; vertical-align: middle; font-variant-numeric: tabular-nums; font-weight: 400; border-bottom: 1px solid rgba(0, 0, 0, 0.12);">78.8%</td><td style="padding: 0.470903rem 0.770569rem; text-align: center; vertical-align: middle; font-variant-numeric: tabular-nums; font-weight: 400; border-bottom: 1px solid rgba(0, 0, 0, 0.12);">86.3%</td><td style="padding: 0.470903rem 0.770569rem; text-align: center; vertical-align: middle; font-variant-numeric: tabular-nums; font-weight: 400; border-bottom: 1px solid rgba(0, 0, 0, 0.12); border-left: 1px solid rgba(0, 0, 0, 0.12);">–</td><td style="padding: 0.470903rem 0.770569rem; text-align: center; vertical-align: middle; font-variant-numeric: tabular-nums; font-weight: 400; border-bottom: 1px solid rgba(0, 0, 0, 0.12);">–</td><td style="padding: 0.470903rem 0.770569rem; text-align: center; vertical-align: middle; font-variant-numeric: tabular-nums; font-weight: 500; background: rgb(251, 236, 191); border-bottom: 1px solid rgba(0, 0, 0, 0.12);">98.5%</td></tr><tr><td style="padding: 0.470903rem 0.68495rem; text-align: left; vertical-align: middle; max-width: 188.361px; border-bottom: 1px solid rgba(0, 0, 0, 0.12);"><span style="display: block; line-height: 1.22; white-space: nowrap;">CritPt</span><span style="display: block; font-size: 0.88em; line-height: 1.25; color: rgb(107, 107, 107); margin-top: 0.18rem; white-space: normal;">Score</span></td><td style="padding: 0.470903rem 0.770569rem; text-align: center; vertical-align: middle; font-variant-numeric: tabular-nums; font-weight: 500; border-bottom: 1px solid rgba(0, 0, 0, 0.12); border-left: 1.5px solid rgba(0, 0, 0, 0.16); border-right: 1.5px solid rgba(0, 0, 0, 0.16);">8.3%</td><td style="padding: 0.470903rem 0.770569rem; text-align: center; vertical-align: middle; font-variant-numeric: tabular-nums; font-weight: 400; border-bottom: 1px solid rgba(0, 0, 0, 0.12);">1.7%</td><td style="padding: 0.470903rem 0.770569rem; text-align: center; vertical-align: middle; font-variant-numeric: tabular-nums; font-weight: 400; border-bottom: 1px solid rgba(0, 0, 0, 0.12);">3.7%</td><td style="padding: 0.470903rem 0.770569rem; text-align: center; vertical-align: middle; font-variant-numeric: tabular-nums; font-weight: 400; border-bottom: 1px solid rgba(0, 0, 0, 0.12);">0.6%</td><td style="padding: 0.470903rem 0.770569rem; text-align: center; vertical-align: middle; font-variant-numeric: tabular-nums; font-weight: 400; border-bottom: 1px solid rgba(0, 0, 0, 0.12);">7.1%</td><td style="padding: 0.470903rem 0.770569rem; text-align: center; vertical-align: middle; font-variant-numeric: tabular-nums; font-weight: 400; border-bottom: 1px solid rgba(0, 0, 0, 0.12);">3.1%</td><td style="padding: 0.470903rem 0.770569rem; text-align: center; vertical-align: middle; font-variant-numeric: tabular-nums; font-weight: 400; border-bottom: 1px solid rgba(0, 0, 0, 0.12);">5.4%</td><td style="padding: 0.470903rem 0.770569rem; text-align: center; vertical-align: middle; font-variant-numeric: tabular-nums; font-weight: 400; border-bottom: 1px solid rgba(0, 0, 0, 0.12); border-left: 1px solid rgba(0, 0, 0, 0.12);">0.0%</td><td style="padding: 0.470903rem 0.770569rem; text-align: center; vertical-align: middle; font-variant-numeric: tabular-nums; font-weight: 400; border-bottom: 1px solid rgba(0, 0, 0, 0.12);">0.0%</td><td style="padding: 0.470903rem 0.770569rem; text-align: center; vertical-align: middle; font-variant-numeric: tabular-nums; font-weight: 500; background: rgb(251, 236, 191); border-bottom: 1px solid rgba(0, 0, 0, 0.12);">20.6%</td></tr><tr><th scope="row" style="padding: 0.27398rem 0.68495rem; text-align: left; font-size: 0.92em; font-weight: 400; line-height: 1.2; color: rgb(107, 107, 107); background: rgb(242, 242, 242); white-space: nowrap;">Reasoning (abstract)</th><td aria-hidden="true" style="padding: 0.27398rem 0.770569rem; background: rgb(242, 242, 242); border-left: 1.5px solid rgba(0, 0, 0, 0.16); border-right: 1.5px solid rgba(0, 0, 0, 0.16);"></td><td aria-hidden="true" style="padding: 0.27398rem 0.770569rem; background: rgb(242, 242, 242);"></td><td aria-hidden="true" style="padding: 0.27398rem 0.770569rem; background: rgb(242, 242, 242);"></td><td aria-hidden="true" style="padding: 0.27398rem 0.770569rem; background: rgb(242, 242, 242);"></td><td aria-hidden="true" style="padding: 0.27398rem 0.770569rem; background: rgb(242, 242, 242);"></td><td aria-hidden="true" style="padding: 0.27398rem 0.770569rem; background: rgb(242, 242, 242);"></td><td aria-hidden="true" style="padding: 0.27398rem 0.770569rem; background: rgb(242, 242, 242);"></td><td aria-hidden="true" style="padding: 0.27398rem 0.770569rem; background: rgb(242, 242, 242); border-left: 1px solid rgba(0, 0, 0, 0.12);"></td><td aria-hidden="true" style="padding: 0.27398rem 0.770569rem; background: rgb(242, 242, 242);"></td><td aria-hidden="true" style="padding: 0.27398rem 0.770569rem; background: rgb(242, 242, 242);"></td></tr><tr><td style="padding: 0.470903rem 0.68495rem; text-align: left; vertical-align: middle; max-width: 188.361px; border-bottom: 1px solid rgba(0, 0, 0, 0.12);"><span style="display: block; line-height: 1.22; white-space: nowrap;">ARC-AGI-1</span><span style="display: block; font-size: 0.88em; line-height: 1.25; color: rgb(107, 107, 107); margin-top: 0.18rem; white-space: normal;">Score</span></td><td style="padding: 0.470903rem 0.770569rem; text-align: center; vertical-align: middle; font-variant-numeric: tabular-nums; font-weight: 500; border-bottom: 1px solid rgba(0, 0, 0, 0.12); border-left: 1.5px solid rgba(0, 0, 0, 0.16); border-right: 1.5px solid rgba(0, 0, 0, 0.16);">84.0%</td><td style="padding: 0.470903rem 0.770569rem; text-align: center; vertical-align: middle; font-variant-numeric: tabular-nums; font-weight: 400; border-bottom: 1px solid rgba(0, 0, 0, 0.12);">–</td><td style="padding: 0.470903rem 0.770569rem; text-align: center; vertical-align: middle; font-variant-numeric: tabular-nums; font-weight: 400; border-bottom: 1px solid rgba(0, 0, 0, 0.12);">–</td><td style="padding: 0.470903rem 0.770569rem; text-align: center; vertical-align: middle; font-variant-numeric: tabular-nums; font-weight: 400; border-bottom: 1px solid rgba(0, 0, 0, 0.12);">–</td><td style="padding: 0.470903rem 0.770569rem; text-align: center; vertical-align: middle; font-variant-numeric: tabular-nums; font-weight: 400; border-bottom: 1px solid rgba(0, 0, 0, 0.12);">–</td><td style="padding: 0.470903rem 0.770569rem; text-align: center; vertical-align: middle; font-variant-numeric: tabular-nums; font-weight: 400; border-bottom: 1px solid rgba(0, 0, 0, 0.12);">–</td><td style="padding: 0.470903rem 0.770569rem; text-align: center; vertical-align: middle; font-variant-numeric: tabular-nums; font-weight: 400; border-bottom: 1px solid rgba(0, 0, 0, 0.12);">79.5%</td><td style="padding: 0.470903rem 0.770569rem; text-align: center; vertical-align: middle; font-variant-numeric: tabular-nums; font-weight: 400; border-bottom: 1px solid rgba(0, 0, 0, 0.12); border-left: 1px solid rgba(0, 0, 0, 0.12);">47.7%</td><td style="padding: 0.470903rem 0.770569rem; text-align: center; vertical-align: middle; font-variant-numeric: tabular-nums; font-weight: 400; border-bottom: 1px solid rgba(0, 0, 0, 0.12);">–</td><td style="padding: 0.470903rem 0.770569rem; text-align: center; vertical-align: middle; font-variant-numeric: tabular-nums; font-weight: 500; background: rgb(251, 236, 191); border-bottom: 1px solid rgba(0, 0, 0, 0.12);">87.7%</td></tr><tr><td style="padding: 0.470903rem 0.68495rem; text-align: left; vertical-align: middle; max-width: 188.361px; border-bottom: 1px solid rgba(0, 0, 0, 0.12);"><span style="display: block; line-height: 1.22; white-space: nowrap;">ARC-AGI-2</span><span style="display: block; font-size: 0.88em; line-height: 1.25; color: rgb(107, 107, 107); margin-top: 0.18rem; white-space: normal;">Score</span></td><td style="padding: 0.470903rem 0.770569rem; text-align: center; vertical-align: middle; font-variant-numeric: tabular-nums; font-weight: 500; border-bottom: 1px solid rgba(0, 0, 0, 0.12); border-left: 1.5px solid rgba(0, 0, 0, 0.16); border-right: 1.5px solid rgba(0, 0, 0, 0.16);">40.1%</td><td style="padding: 0.470903rem 0.770569rem; text-align: center; vertical-align: middle; font-variant-numeric: tabular-nums; font-weight: 400; border-bottom: 1px solid rgba(0, 0, 0, 0.12);">–</td><td style="padding: 0.470903rem 0.770569rem; text-align: center; vertical-align: middle; font-variant-numeric: tabular-nums; font-weight: 400; border-bottom: 1px solid rgba(0, 0, 0, 0.12);">–</td><td style="padding: 0.470903rem 0.770569rem; text-align: center; vertical-align: middle; font-variant-numeric: tabular-nums; font-weight: 400; border-bottom: 1px solid rgba(0, 0, 0, 0.12);">–</td><td style="padding: 0.470903rem 0.770569rem; text-align: center; vertical-align: middle; font-variant-numeric: tabular-nums; font-weight: 400; border-bottom: 1px solid rgba(0, 0, 0, 0.12);">–</td><td style="padding: 0.470903rem 0.770569rem; text-align: center; vertical-align: middle; font-variant-numeric: tabular-nums; font-weight: 400; border-bottom: 1px solid rgba(0, 0, 0, 0.12);">–</td><td style="padding: 0.470903rem 0.770569rem; text-align: center; vertical-align: middle; font-variant-numeric: tabular-nums; font-weight: 400; border-bottom: 1px solid rgba(0, 0, 0, 0.12);">36.5%</td><td style="padding: 0.470903rem 0.770569rem; text-align: center; vertical-align: middle; font-variant-numeric: tabular-nums; font-weight: 400; border-bottom: 1px solid rgba(0, 0, 0, 0.12); border-left: 1px solid rgba(0, 0, 0, 0.12);">4.0%</td><td style="padding: 0.470903rem 0.770569rem; text-align: center; vertical-align: middle; font-variant-numeric: tabular-nums; font-weight: 400; border-bottom: 1px solid rgba(0, 0, 0, 0.12);">–</td><td style="padding: 0.470903rem 0.770569rem; text-align: center; vertical-align: middle; font-variant-numeric: tabular-nums; font-weight: 500; background: rgb(251, 236, 191); border-bottom: 1px solid rgba(0, 0, 0, 0.12);">47.6%</td></tr><tr><th scope="row" style="padding: 0.27398rem 0.68495rem; text-align: left; font-size: 0.92em; font-weight: 400; line-height: 1.2; color: rgb(107, 107, 107); background: rgb(242, 242, 242); white-space: nowrap;">Factuality</th><td aria-hidden="true" style="padding: 0.27398rem 0.770569rem; background: rgb(242, 242, 242); border-left: 1.5px solid rgba(0, 0, 0, 0.16); border-right: 1.5px solid rgba(0, 0, 0, 0.16);"></td><td aria-hidden="true" style="padding: 0.27398rem 0.770569rem; background: rgb(242, 242, 242);"></td><td aria-hidden="true" style="padding: 0.27398rem 0.770569rem; background: rgb(242, 242, 242);"></td><td aria-hidden="true" style="padding: 0.27398rem 0.770569rem; background: rgb(242, 242, 242);"></td><td aria-hidden="true" style="padding: 0.27398rem 0.770569rem; background: rgb(242, 242, 242);"></td><td aria-hidden="true" style="padding: 0.27398rem 0.770569rem; background: rgb(242, 242, 242);"></td><td aria-hidden="true" style="padding: 0.27398rem 0.770569rem; background: rgb(242, 242, 242);"></td><td aria-hidden="true" style="padding: 0.27398rem 0.770569rem; background: rgb(242, 242, 242); border-left: 1px solid rgba(0, 0, 0, 0.12);"></td><td aria-hidden="true" style="padding: 0.27398rem 0.770569rem; background: rgb(242, 242, 242);"></td><td aria-hidden="true" style="padding: 0.27398rem 0.770569rem; background: rgb(242, 242, 242);"></td></tr><tr><td style="padding: 0.470903rem 0.68495rem; text-align: left; vertical-align: middle; max-width: 188.361px; border-bottom: 1px solid rgba(0, 0, 0, 0.12);"><span style="display: block; line-height: 1.22; white-space: nowrap;">SimpleQA Verified</span><span style="display: block; font-size: 0.88em; line-height: 1.25; color: rgb(107, 107, 107); margin-top: 0.18rem; white-space: normal;">Score</span></td><td style="padding: 0.470903rem 0.770569rem; text-align: center; vertical-align: middle; font-variant-numeric: tabular-nums; font-weight: 500; border-bottom: 1px solid rgba(0, 0, 0, 0.12); border-left: 1.5px solid rgba(0, 0, 0, 0.16); border-right: 1.5px solid rgba(0, 0, 0, 0.16);">20.6%</td><td style="padding: 0.470903rem 0.770569rem; text-align: center; vertical-align: middle; font-variant-numeric: tabular-nums; font-weight: 400; border-bottom: 1px solid rgba(0, 0, 0, 0.12);">26.0%</td><td style="padding: 0.470903rem 0.770569rem; text-align: center; vertical-align: middle; font-variant-numeric: tabular-nums; font-weight: 400; border-bottom: 1px solid rgba(0, 0, 0, 0.12);">16.1%</td><td style="padding: 0.470903rem 0.770569rem; text-align: center; vertical-align: middle; font-variant-numeric: tabular-nums; font-weight: 400; border-bottom: 1px solid rgba(0, 0, 0, 0.12);">13.5%</td><td style="padding: 0.470903rem 0.770569rem; text-align: center; vertical-align: middle; font-variant-numeric: tabular-nums; font-weight: 400; border-bottom: 1px solid rgba(0, 0, 0, 0.12);">34.1%</td><td style="padding: 0.470903rem 0.770569rem; text-align: center; vertical-align: middle; font-variant-numeric: tabular-nums; font-weight: 400; border-bottom: 1px solid rgba(0, 0, 0, 0.12);">32.4%</td><td style="padding: 0.470903rem 0.770569rem; text-align: center; vertical-align: middle; font-variant-numeric: tabular-nums; font-weight: 400; border-bottom: 1px solid rgba(0, 0, 0, 0.12);">43.9%</td><td style="padding: 0.470903rem 0.770569rem; text-align: center; vertical-align: middle; font-variant-numeric: tabular-nums; font-weight: 400; border-bottom: 1px solid rgba(0, 0, 0, 0.12); border-left: 1px solid rgba(0, 0, 0, 0.12);">5.9%</td><td style="padding: 0.470903rem 0.770569rem; text-align: center; vertical-align: middle; font-variant-numeric: tabular-nums; font-weight: 500; background: rgb(251, 236, 191); border-bottom: 1px solid rgba(0, 0, 0, 0.12);">44.1%</td><td style="padding: 0.470903rem 0.770569rem; text-align: center; vertical-align: middle; font-variant-numeric: tabular-nums; font-weight: 400; border-bottom: 1px solid rgba(0, 0, 0, 0.12);">41.7%</td></tr><tr><td style="padding: 0.470903rem 0.68495rem; text-align: left; vertical-align: middle; max-width: 188.361px; border-bottom: 1px solid rgba(0, 0, 0, 0.12);"><span style="display: block; line-height: 1.22; white-space: nowrap;">AA Omniscience</span><span style="display: block; font-size: 0.88em; line-height: 1.25; color: rgb(107, 107, 107); margin-top: 0.18rem; white-space: normal;">Score</span></td><td style="padding: 0.470903rem 0.770569rem; text-align: center; vertical-align: middle; font-variant-numeric: tabular-nums; font-weight: 500; border-bottom: 1px solid rgba(0, 0, 0, 0.12); border-left: 1.5px solid rgba(0, 0, 0, 0.16); border-right: 1.5px solid rgba(0, 0, 0, 0.16);">-9</td><td style="padding: 0.470903rem 0.770569rem; text-align: center; vertical-align: middle; font-variant-numeric: tabular-nums; font-weight: 400; border-bottom: 1px solid rgba(0, 0, 0, 0.12);">-29.8</td><td style="padding: 0.470903rem 0.770569rem; text-align: center; vertical-align: middle; font-variant-numeric: tabular-nums; font-weight: 400; border-bottom: 1px solid rgba(0, 0, 0, 0.12);">-9.3</td><td style="padding: 0.470903rem 0.770569rem; text-align: center; vertical-align: middle; font-variant-numeric: tabular-nums; font-weight: 400; border-bottom: 1px solid rgba(0, 0, 0, 0.12);">0.7</td><td style="padding: 0.470903rem 0.770569rem; text-align: center; vertical-align: middle; font-variant-numeric: tabular-nums; font-weight: 400; border-bottom: 1px solid rgba(0, 0, 0, 0.12);">-22.9</td><td style="padding: 0.470903rem 0.770569rem; text-align: center; vertical-align: middle; font-variant-numeric: tabular-nums; font-weight: 400; border-bottom: 1px solid rgba(0, 0, 0, 0.12);">-1</td><td style="padding: 0.470903rem 0.770569rem; text-align: center; vertical-align: middle; font-variant-numeric: tabular-nums; font-weight: 400; border-bottom: 1px solid rgba(0, 0, 0, 0.12);">2.1</td><td style="padding: 0.470903rem 0.770569rem; text-align: center; vertical-align: middle; font-variant-numeric: tabular-nums; font-weight: 400; border-bottom: 1px solid rgba(0, 0, 0, 0.12); border-left: 1px solid rgba(0, 0, 0, 0.12);">-4.2</td><td style="padding: 0.470903rem 0.770569rem; text-align: center; vertical-align: middle; font-variant-numeric: tabular-nums; font-weight: 500; background: rgb(251, 236, 191); border-bottom: 1px solid rgba(0, 0, 0, 0.12);">6.9</td><td style="padding: 0.470903rem 0.770569rem; text-align: center; vertical-align: middle; font-variant-numeric: tabular-nums; font-weight: 400; border-bottom: 1px solid rgba(0, 0, 0, 0.12);">-11.6</td></tr><tr><th scope="row" style="padding: 0.27398rem 0.68495rem; text-align: left; font-size: 0.92em; font-weight: 400; line-height: 1.2; color: rgb(107, 107, 107); background: rgb(242, 242, 242); white-space: nowrap;">Chat</th><td aria-hidden="true" style="padding: 0.27398rem 0.770569rem; background: rgb(242, 242, 242); border-left: 1.5px solid rgba(0, 0, 0, 0.16); border-right: 1.5px solid rgba(0, 0, 0, 0.16);"></td><td aria-hidden="true" style="padding: 0.27398rem 0.770569rem; background: rgb(242, 242, 242);"></td><td aria-hidden="true" style="padding: 0.27398rem 0.770569rem; background: rgb(242, 242, 242);"></td><td aria-hidden="true" style="padding: 0.27398rem 0.770569rem; background: rgb(242, 242, 242);"></td><td aria-hidden="true" style="padding: 0.27398rem 0.770569rem; background: rgb(242, 242, 242);"></td><td aria-hidden="true" style="padding: 0.27398rem 0.770569rem; background: rgb(242, 242, 242);"></td><td aria-hidden="true" style="padding: 0.27398rem 0.770569rem; background: rgb(242, 242, 242);"></td><td aria-hidden="true" style="padding: 0.27398rem 0.770569rem; background: rgb(242, 242, 242); border-left: 1px solid rgba(0, 0, 0, 0.12);"></td><td aria-hidden="true" style="padding: 0.27398rem 0.770569rem; background: rgb(242, 242, 242);"></td><td aria-hidden="true" style="padding: 0.27398rem 0.770569rem; background: rgb(242, 242, 242);"></td></tr><tr><td style="padding: 0.470903rem 0.68495rem; text-align: left; vertical-align: middle; max-width: 188.361px; border-bottom: 1px solid rgba(0, 0, 0, 0.12);"><span style="display: block; line-height: 1.22; white-space: nowrap;">IFBench</span><span style="display: block; font-size: 0.88em; line-height: 1.25; color: rgb(107, 107, 107); margin-top: 0.18rem; white-space: normal;">Score</span></td><td style="padding: 0.470903rem 0.770569rem; text-align: center; vertical-align: middle; font-variant-numeric: tabular-nums; font-weight: 500; background: rgb(251, 236, 191); border-bottom: 1px solid rgba(0, 0, 0, 0.12); border-left: 1.5px solid rgba(0, 0, 0, 0.16); border-right: 1.5px solid rgba(0, 0, 0, 0.16);">82.2%</td><td style="padding: 0.470903rem 0.770569rem; text-align: center; vertical-align: middle; font-variant-numeric: tabular-nums; font-weight: 400; border-bottom: 1px solid rgba(0, 0, 0, 0.12);">78.8%</td><td style="padding: 0.470903rem 0.770569rem; text-align: center; vertical-align: middle; font-variant-numeric: tabular-nums; font-weight: 400; border-bottom: 1px solid rgba(0, 0, 0, 0.12);">67.1%</td><td style="padding: 0.470903rem 0.770569rem; text-align: center; vertical-align: middle; font-variant-numeric: tabular-nums; font-weight: 400; border-bottom: 1px solid rgba(0, 0, 0, 0.12);">75.7%</td><td style="padding: 0.470903rem 0.770569rem; text-align: center; vertical-align: middle; font-variant-numeric: tabular-nums; font-weight: 400; border-bottom: 1px solid rgba(0, 0, 0, 0.12);">79.2%</td><td style="padding: 0.470903rem 0.770569rem; text-align: center; vertical-align: middle; font-variant-numeric: tabular-nums; font-weight: 400; border-bottom: 1px solid rgba(0, 0, 0, 0.12);">81.4%</td><td style="padding: 0.470903rem 0.770569rem; text-align: center; vertical-align: middle; font-variant-numeric: tabular-nums; font-weight: 400; border-bottom: 1px solid rgba(0, 0, 0, 0.12);">79.8%</td><td style="padding: 0.470903rem 0.770569rem; text-align: center; vertical-align: middle; font-variant-numeric: tabular-nums; font-weight: 400; border-bottom: 1px solid rgba(0, 0, 0, 0.12); border-left: 1px solid rgba(0, 0, 0, 0.12);">54.3%</td><td style="padding: 0.470903rem 0.770569rem; text-align: center; vertical-align: middle; font-variant-numeric: tabular-nums; font-weight: 400; border-bottom: 1px solid rgba(0, 0, 0, 0.12);">78.6%</td><td style="padding: 0.470903rem 0.770569rem; text-align: center; vertical-align: middle; font-variant-numeric: tabular-nums; font-weight: 400; border-bottom: 1px solid rgba(0, 0, 0, 0.12);">67.3%</td></tr><tr><td style="padding: 0.470903rem 0.68495rem; text-align: left; vertical-align: middle; max-width: 188.361px; border-bottom: 1px solid rgba(0, 0, 0, 0.12);"><span style="display: block; line-height: 1.22; white-space: nowrap;">Global-MMLU-Lite</span><span style="display: block; font-size: 0.88em; line-height: 1.25; color: rgb(107, 107, 107); margin-top: 0.18rem; white-space: normal;">Score</span></td><td style="padding: 0.470903rem 0.770569rem; text-align: center; vertical-align: middle; font-variant-numeric: tabular-nums; font-weight: 500; border-bottom: 1px solid rgba(0, 0, 0, 0.12); border-left: 1.5px solid rgba(0, 0, 0, 0.16); border-right: 1.5px solid rgba(0, 0, 0, 0.16);">86.7%</td><td style="padding: 0.470903rem 0.770569rem; text-align: center; vertical-align: middle; font-variant-numeric: tabular-nums; font-weight: 500; background: rgb(251, 236, 191); border-bottom: 1px solid rgba(0, 0, 0, 0.12);">90.0%</td><td style="padding: 0.470903rem 0.770569rem; text-align: center; vertical-align: middle; font-variant-numeric: tabular-nums; font-weight: 400; border-bottom: 1px solid rgba(0, 0, 0, 0.12);">83.5%</td><td style="padding: 0.470903rem 0.770569rem; text-align: center; vertical-align: middle; font-variant-numeric: tabular-nums; font-weight: 400; border-bottom: 1px solid rgba(0, 0, 0, 0.12);">83.9%</td><td style="padding: 0.470903rem 0.770569rem; text-align: center; vertical-align: middle; font-variant-numeric: tabular-nums; font-weight: 400; border-bottom: 1px solid rgba(0, 0, 0, 0.12);">88.4%</td><td style="padding: 0.470903rem 0.770569rem; text-align: center; vertical-align: middle; font-variant-numeric: tabular-nums; font-weight: 400; border-bottom: 1px solid rgba(0, 0, 0, 0.12);">85.6%</td><td style="padding: 0.470903rem 0.770569rem; text-align: center; vertical-align: middle; font-variant-numeric: tabular-nums; font-weight: 400; border-bottom: 1px solid rgba(0, 0, 0, 0.12);">88.7%</td><td style="padding: 0.470903rem 0.770569rem; text-align: center; vertical-align: middle; font-variant-numeric: tabular-nums; font-weight: 400; border-bottom: 1px solid rgba(0, 0, 0, 0.12); border-left: 1px solid rgba(0, 0, 0, 0.12);">83.4%</td><td style="padding: 0.470903rem 0.770569rem; text-align: center; vertical-align: middle; font-variant-numeric: tabular-nums; font-weight: 400; border-bottom: 1px solid rgba(0, 0, 0, 0.12);">89.4%</td><td style="padding: 0.470903rem 0.770569rem; text-align: center; vertical-align: middle; font-variant-numeric: tabular-nums; font-weight: 400; border-bottom: 1px solid rgba(0, 0, 0, 0.12);">88.7%</td></tr><tr><th scope="row" style="padding: 0.27398rem 0.68495rem; text-align: left; font-size: 0.92em; font-weight: 400; line-height: 1.2; color: rgb(107, 107, 107); background: rgb(242, 242, 242); white-space: nowrap;">Safety</th><td aria-hidden="true" style="padding: 0.27398rem 0.770569rem; background: rgb(242, 242, 242); border-left: 1.5px solid rgba(0, 0, 0, 0.16); border-right: 1.5px solid rgba(0, 0, 0, 0.16);"></td><td aria-hidden="true" style="padding: 0.27398rem 0.770569rem; background: rgb(242, 242, 242);"></td><td aria-hidden="true" style="padding: 0.27398rem 0.770569rem; background: rgb(242, 242, 242);"></td><td aria-hidden="true" style="padding: 0.27398rem 0.770569rem; background: rgb(242, 242, 242);"></td><td aria-hidden="true" style="padding: 0.27398rem 0.770569rem; background: rgb(242, 242, 242);"></td><td aria-hidden="true" style="padding: 0.27398rem 0.770569rem; background: rgb(242, 242, 242);"></td><td aria-hidden="true" style="padding: 0.27398rem 0.770569rem; background: rgb(242, 242, 242);"></td><td aria-hidden="true" style="padding: 0.27398rem 0.770569rem; background: rgb(242, 242, 242); border-left: 1px solid rgba(0, 0, 0, 0.12);"></td><td aria-hidden="true" style="padding: 0.27398rem 0.770569rem; background: rgb(242, 242, 242);"></td><td aria-hidden="true" style="padding: 0.27398rem 0.770569rem; background: rgb(242, 242, 242);"></td></tr><tr><td style="padding: 0.470903rem 0.68495rem; text-align: left; vertical-align: middle; max-width: 188.361px; border-bottom: 1px solid rgba(0, 0, 0, 0.12);"><span style="display: block; line-height: 1.22; white-space: nowrap;">StrongREJECT (none)</span><span style="display: block; font-size: 0.88em; line-height: 1.25; color: rgb(107, 107, 107); margin-top: 0.18rem; white-space: normal;">Score</span></td><td style="padding: 0.470903rem 0.770569rem; text-align: center; vertical-align: middle; font-variant-numeric: tabular-nums; font-weight: 500; border-bottom: 1px solid rgba(0, 0, 0, 0.12); border-left: 1.5px solid rgba(0, 0, 0, 0.16); border-right: 1.5px solid rgba(0, 0, 0, 0.16);">98.4%</td><td style="padding: 0.470903rem 0.770569rem; text-align: center; vertical-align: middle; font-variant-numeric: tabular-nums; font-weight: 500; background: rgb(251, 236, 191); border-bottom: 1px solid rgba(0, 0, 0, 0.12);">99.4%</td><td style="padding: 0.470903rem 0.770569rem; text-align: center; vertical-align: middle; font-variant-numeric: tabular-nums; font-weight: 400; border-bottom: 1px solid rgba(0, 0, 0, 0.12);">99.3%</td><td style="padding: 0.470903rem 0.770569rem; text-align: center; vertical-align: middle; font-variant-numeric: tabular-nums; font-weight: 500; background: rgb(251, 236, 191); border-bottom: 1px solid rgba(0, 0, 0, 0.12);">99.4%</td><td style="padding: 0.470903rem 0.770569rem; text-align: center; vertical-align: middle; font-variant-numeric: tabular-nums; font-weight: 400; border-bottom: 1px solid rgba(0, 0, 0, 0.12);">97.4%</td><td style="padding: 0.470903rem 0.770569rem; text-align: center; vertical-align: middle; font-variant-numeric: tabular-nums; font-weight: 400; border-bottom: 1px solid rgba(0, 0, 0, 0.12);">98.7%</td><td style="padding: 0.470903rem 0.770569rem; text-align: center; vertical-align: middle; font-variant-numeric: tabular-nums; font-weight: 400; border-bottom: 1px solid rgba(0, 0, 0, 0.12);">98.6%</td><td style="padding: 0.470903rem 0.770569rem; text-align: center; vertical-align: middle; font-variant-numeric: tabular-nums; font-weight: 400; border-bottom: 1px solid rgba(0, 0, 0, 0.12); border-left: 1px solid rgba(0, 0, 0, 0.12);">98.6%</td><td style="padding: 0.470903rem 0.770569rem; text-align: center; vertical-align: middle; font-variant-numeric: tabular-nums; font-weight: 400; border-bottom: 1px solid rgba(0, 0, 0, 0.12);">97.6%</td><td style="padding: 0.470903rem 0.770569rem; text-align: center; vertical-align: middle; font-variant-numeric: tabular-nums; font-weight: 400; border-bottom: 1px solid rgba(0, 0, 0, 0.12);">98.7%</td></tr><tr><td style="padding: 0.470903rem 0.68495rem; text-align: left; vertical-align: middle; max-width: 188.361px; border-bottom: 1px solid rgba(0, 0, 0, 0.12);"><span style="display: block; line-height: 1.22; white-space: nowrap;">FORTRESS (adversarial)</span><span style="display: block; font-size: 0.88em; line-height: 1.25; color: rgb(107, 107, 107); margin-top: 0.18rem; white-space: normal;">Score</span></td><td style="padding: 0.470903rem 0.770569rem; text-align: center; vertical-align: middle; font-variant-numeric: tabular-nums; font-weight: 500; border-bottom: 1px solid rgba(0, 0, 0, 0.12); border-left: 1.5px solid rgba(0, 0, 0, 0.16); border-right: 1.5px solid rgba(0, 0, 0, 0.16);">71.6%</td><td style="padding: 0.470903rem 0.770569rem; text-align: center; vertical-align: middle; font-variant-numeric: tabular-nums; font-weight: 400; border-bottom: 1px solid rgba(0, 0, 0, 0.12);">77.3%</td><td style="padding: 0.470903rem 0.770569rem; text-align: center; vertical-align: middle; font-variant-numeric: tabular-nums; font-weight: 400; border-bottom: 1px solid rgba(0, 0, 0, 0.12);">64.8%</td><td style="padding: 0.470903rem 0.770569rem; text-align: center; vertical-align: middle; font-variant-numeric: tabular-nums; font-weight: 400; border-bottom: 1px solid rgba(0, 0, 0, 0.12);">86.3%</td><td style="padding: 0.470903rem 0.770569rem; text-align: center; vertical-align: middle; font-variant-numeric: tabular-nums; font-weight: 400; border-bottom: 1px solid rgba(0, 0, 0, 0.12);">32.0%</td><td style="padding: 0.470903rem 0.770569rem; text-align: center; vertical-align: middle; font-variant-numeric: tabular-nums; font-weight: 400; border-bottom: 1px solid rgba(0, 0, 0, 0.12);">77.6%</td><td style="padding: 0.470903rem 0.770569rem; text-align: center; vertical-align: middle; font-variant-numeric: tabular-nums; font-weight: 400; border-bottom: 1px solid rgba(0, 0, 0, 0.12);">78.0%</td><td style="padding: 0.470903rem 0.770569rem; text-align: center; vertical-align: middle; font-variant-numeric: tabular-nums; font-weight: 500; background: rgb(251, 236, 191); border-bottom: 1px solid rgba(0, 0, 0, 0.12); border-left: 1px solid rgba(0, 0, 0, 0.12);">91.3%</td><td style="padding: 0.470903rem 0.770569rem; text-align: center; vertical-align: middle; font-variant-numeric: tabular-nums; font-weight: 400; border-bottom: 1px solid rgba(0, 0, 0, 0.12);">70.7%</td><td style="padding: 0.470903rem 0.770569rem; text-align: center; vertical-align: middle; font-variant-numeric: tabular-nums; font-weight: 400; border-bottom: 1px solid rgba(0, 0, 0, 0.12);">83.8%</td></tr><tr><td style="padding: 0.470903rem 0.68495rem; text-align: left; vertical-align: middle; max-width: 188.361px; border-bottom: 1px solid rgba(0, 0, 0, 0.12);"><span style="display: block; line-height: 1.22; white-space: nowrap;">FORTRESS (benign)</span><span style="display: block; font-size: 0.88em; line-height: 1.25; color: rgb(107, 107, 107); margin-top: 0.18rem; white-space: normal;">Score</span></td><td style="padding: 0.470903rem 0.770569rem; text-align: center; vertical-align: middle; font-variant-numeric: tabular-nums; font-weight: 500; border-bottom: 1px solid rgba(0, 0, 0, 0.12); border-left: 1.5px solid rgba(0, 0, 0, 0.16); border-right: 1.5px solid rgba(0, 0, 0, 0.16);">96.9%</td><td style="padding: 0.470903rem 0.770569rem; text-align: center; vertical-align: middle; font-variant-numeric: tabular-nums; font-weight: 400; border-bottom: 1px solid rgba(0, 0, 0, 0.12);">95.4%</td><td style="padding: 0.470903rem 0.770569rem; text-align: center; vertical-align: middle; font-variant-numeric: tabular-nums; font-weight: 400; border-bottom: 1px solid rgba(0, 0, 0, 0.12);">94.6%</td><td style="padding: 0.470903rem 0.770569rem; text-align: center; vertical-align: middle; font-variant-numeric: tabular-nums; font-weight: 400; border-bottom: 1px solid rgba(0, 0, 0, 0.12);">90.1%</td><td style="padding: 0.470903rem 0.770569rem; text-align: center; vertical-align: middle; font-variant-numeric: tabular-nums; font-weight: 500; background: rgb(251, 236, 191); border-bottom: 1px solid rgba(0, 0, 0, 0.12);">99.2%</td><td style="padding: 0.470903rem 0.770569rem; text-align: center; vertical-align: middle; font-variant-numeric: tabular-nums; font-weight: 400; border-bottom: 1px solid rgba(0, 0, 0, 0.12);">90.5%</td><td style="padding: 0.470903rem 0.770569rem; text-align: center; vertical-align: middle; font-variant-numeric: tabular-nums; font-weight: 400; border-bottom: 1px solid rgba(0, 0, 0, 0.12);">95.9%</td><td style="padding: 0.470903rem 0.770569rem; text-align: center; vertical-align: middle; font-variant-numeric: tabular-nums; font-weight: 400; border-bottom: 1px solid rgba(0, 0, 0, 0.12); border-left: 1px solid rgba(0, 0, 0, 0.12);">94.1%</td><td style="padding: 0.470903rem 0.770569rem; text-align: center; vertical-align: middle; font-variant-numeric: tabular-nums; font-weight: 400; border-bottom: 1px solid rgba(0, 0, 0, 0.12);">95.5%</td><td style="padding: 0.470903rem 0.770569rem; text-align: center; vertical-align: middle; font-variant-numeric: tabular-nums; font-weight: 400; border-bottom: 1px solid rgba(0, 0, 0, 0.12);">97.8%</td></tr><tr><th scope="row" style="padding: 0.27398rem 0.68495rem; text-align: left; font-size: 0.92em; font-weight: 400; line-height: 1.2; color: rgb(107, 107, 107); background: rgb(242, 242, 242); white-space: nowrap;">Vision</th><td aria-hidden="true" style="padding: 0.27398rem 0.770569rem; background: rgb(242, 242, 242); border-left: 1.5px solid rgba(0, 0, 0, 0.16); border-right: 1.5px solid rgba(0, 0, 0, 0.16);"></td><td aria-hidden="true" style="padding: 0.27398rem 0.770569rem; background: rgb(242, 242, 242);"></td><td aria-hidden="true" style="padding: 0.27398rem 0.770569rem; background: rgb(242, 242, 242);"></td><td aria-hidden="true" style="padding: 0.27398rem 0.770569rem; background: rgb(242, 242, 242);"></td><td aria-hidden="true" style="padding: 0.27398rem 0.770569rem; background: rgb(242, 242, 242);"></td><td aria-hidden="true" style="padding: 0.27398rem 0.770569rem; background: rgb(242, 242, 242);"></td><td aria-hidden="true" style="padding: 0.27398rem 0.770569rem; background: rgb(242, 242, 242);"></td><td aria-hidden="true" style="padding: 0.27398rem 0.770569rem; background: rgb(242, 242, 242); border-left: 1px solid rgba(0, 0, 0, 0.12);"></td><td aria-hidden="true" style="padding: 0.27398rem 0.770569rem; background: rgb(242, 242, 242);"></td><td aria-hidden="true" style="padding: 0.27398rem 0.770569rem; background: rgb(242, 242, 242);"></td></tr><tr><td style="padding: 0.470903rem 0.68495rem; text-align: left; vertical-align: middle; max-width: 188.361px; border-bottom: 1px solid rgba(0, 0, 0, 0.12);"><span style="display: block; line-height: 1.22; white-space: nowrap;">MMMU Pro (Standard 10)</span><span style="display: block; font-size: 0.88em; line-height: 1.25; color: rgb(107, 107, 107); margin-top: 0.18rem; white-space: normal;">Score</span></td><td style="padding: 0.470903rem 0.770569rem; text-align: center; vertical-align: middle; font-variant-numeric: tabular-nums; font-weight: 500; border-bottom: 1px solid rgba(0, 0, 0, 0.12); border-left: 1.5px solid rgba(0, 0, 0, 0.16); border-right: 1.5px solid rgba(0, 0, 0, 0.16);">74.0%</td><td style="padding: 0.470903rem 0.770569rem; text-align: center; vertical-align: middle; font-variant-numeric: tabular-nums; font-weight: 400; border-bottom: 1px solid rgba(0, 0, 0, 0.12);">77.3%</td><td style="padding: 0.470903rem 0.770569rem; text-align: center; vertical-align: middle; font-variant-numeric: tabular-nums; font-weight: 400; border-bottom: 1px solid rgba(0, 0, 0, 0.12);">75.4%</td><td style="padding: 0.470903rem 0.770569rem; text-align: center; vertical-align: middle; font-variant-numeric: tabular-nums; font-weight: 400; border-bottom: 1px solid rgba(0, 0, 0, 0.12);">–</td><td style="padding: 0.470903rem 0.770569rem; text-align: center; vertical-align: middle; font-variant-numeric: tabular-nums; font-weight: 400; border-bottom: 1px solid rgba(0, 0, 0, 0.12);">–</td><td style="padding: 0.470903rem 0.770569rem; text-align: center; vertical-align: middle; font-variant-numeric: tabular-nums; font-weight: 400; border-bottom: 1px solid rgba(0, 0, 0, 0.12);">–</td><td style="padding: 0.470903rem 0.770569rem; text-align: center; vertical-align: middle; font-variant-numeric: tabular-nums; font-weight: 400; border-bottom: 1px solid rgba(0, 0, 0, 0.12);">73.5%</td><td style="padding: 0.470903rem 0.770569rem; text-align: center; vertical-align: middle; font-variant-numeric: tabular-nums; font-weight: 400; border-bottom: 1px solid rgba(0, 0, 0, 0.12); border-left: 1px solid rgba(0, 0, 0, 0.12);">58.6%</td><td style="padding: 0.470903rem 0.770569rem; text-align: center; vertical-align: middle; font-variant-numeric: tabular-nums; font-weight: 500; background: rgb(251, 236, 191); border-bottom: 1px solid rgba(0, 0, 0, 0.12);">79.0%</td><td style="padding: 0.470903rem 0.770569rem; text-align: center; vertical-align: middle; font-variant-numeric: tabular-nums; font-weight: 400; border-bottom: 1px solid rgba(0, 0, 0, 0.12);">78.6%</td></tr><tr><td style="padding: 0.470903rem 0.68495rem; text-align: left; vertical-align: middle; max-width: 188.361px; border-bottom: 1px solid rgba(0, 0, 0, 0.12);"><span style="display: block; line-height: 1.22; white-space: nowrap;">Charxiv RQ</span><span style="display: block; font-size: 0.88em; line-height: 1.25; color: rgb(107, 107, 107); margin-top: 0.18rem; white-space: normal;">Score</span></td><td style="padding: 0.470903rem 0.770569rem; text-align: center; vertical-align: middle; font-variant-numeric: tabular-nums; font-weight: 500; border-bottom: 1px solid rgba(0, 0, 0, 0.12); border-left: 1.5px solid rgba(0, 0, 0, 0.16); border-right: 1.5px solid rgba(0, 0, 0, 0.16);">77.4%</td><td style="padding: 0.470903rem 0.770569rem; text-align: center; vertical-align: middle; font-variant-numeric: tabular-nums; font-weight: 400; border-bottom: 1px solid rgba(0, 0, 0, 0.12);">80.8%</td><td style="padding: 0.470903rem 0.770569rem; text-align: center; vertical-align: middle; font-variant-numeric: tabular-nums; font-weight: 400; border-bottom: 1px solid rgba(0, 0, 0, 0.12);">81.0%</td><td style="padding: 0.470903rem 0.770569rem; text-align: center; vertical-align: middle; font-variant-numeric: tabular-nums; font-weight: 400; border-bottom: 1px solid rgba(0, 0, 0, 0.12);">–</td><td style="padding: 0.470903rem 0.770569rem; text-align: center; vertical-align: middle; font-variant-numeric: tabular-nums; font-weight: 400; border-bottom: 1px solid rgba(0, 0, 0, 0.12);">–</td><td style="padding: 0.470903rem 0.770569rem; text-align: center; vertical-align: middle; font-variant-numeric: tabular-nums; font-weight: 400; border-bottom: 1px solid rgba(0, 0, 0, 0.12);">–</td><td style="padding: 0.470903rem 0.770569rem; text-align: center; vertical-align: middle; font-variant-numeric: tabular-nums; font-weight: 400; border-bottom: 1px solid rgba(0, 0, 0, 0.12);">78.1%</td><td style="padding: 0.470903rem 0.770569rem; text-align: center; vertical-align: middle; font-variant-numeric: tabular-nums; font-weight: 400; border-bottom: 1px solid rgba(0, 0, 0, 0.12); border-left: 1px solid rgba(0, 0, 0, 0.12);">57.4%</td><td style="padding: 0.470903rem 0.770569rem; text-align: center; vertical-align: middle; font-variant-numeric: tabular-nums; font-weight: 400; border-bottom: 1px solid rgba(0, 0, 0, 0.12);">70.0%</td><td style="padding: 0.470903rem 0.770569rem; text-align: center; vertical-align: middle; font-variant-numeric: tabular-nums; font-weight: 500; background: rgb(251, 236, 191); border-bottom: 1px solid rgba(0, 0, 0, 0.12);">81.4%</td></tr><tr><td style="padding: 0.470903rem 0.68495rem; text-align: left; vertical-align: middle; max-width: 188.361px; border-bottom: 1px solid rgba(0, 0, 0, 0.12);"><span style="display: block; line-height: 1.22; white-space: nowrap;">Charxiv RQ (with python)</span><span style="display: block; font-size: 0.88em; line-height: 1.25; color: rgb(107, 107, 107); margin-top: 0.18rem; white-space: normal;">Score</span></td><td style="padding: 0.470903rem 0.770569rem; text-align: center; vertical-align: middle; font-variant-numeric: tabular-nums; font-weight: 500; border-bottom: 1px solid rgba(0, 0, 0, 0.12); border-left: 1.5px solid rgba(0, 0, 0, 0.16); border-right: 1.5px solid rgba(0, 0, 0, 0.16);">81.3%</td><td style="padding: 0.470903rem 0.770569rem; text-align: center; vertical-align: middle; font-variant-numeric: tabular-nums; font-weight: 400; border-bottom: 1px solid rgba(0, 0, 0, 0.12);">–</td><td style="padding: 0.470903rem 0.770569rem; text-align: center; vertical-align: middle; font-variant-numeric: tabular-nums; font-weight: 400; border-bottom: 1px solid rgba(0, 0, 0, 0.12);">–</td><td style="padding: 0.470903rem 0.770569rem; text-align: center; vertical-align: middle; font-variant-numeric: tabular-nums; font-weight: 400; border-bottom: 1px solid rgba(0, 0, 0, 0.12);">–</td><td style="padding: 0.470903rem 0.770569rem; text-align: center; vertical-align: middle; font-variant-numeric: tabular-nums; font-weight: 400; border-bottom: 1px solid rgba(0, 0, 0, 0.12);">–</td><td style="padding: 0.470903rem 0.770569rem; text-align: center; vertical-align: middle; font-variant-numeric: tabular-nums; font-weight: 400; border-bottom: 1px solid rgba(0, 0, 0, 0.12);">–</td><td style="padding: 0.470903rem 0.770569rem; text-align: center; vertical-align: middle; font-variant-numeric: tabular-nums; font-weight: 500; background: rgb(251, 236, 191); border-bottom: 1px solid rgba(0, 0, 0, 0.12);">82.0%</td><td style="padding: 0.470903rem 0.770569rem; text-align: center; vertical-align: middle; font-variant-numeric: tabular-nums; font-weight: 400; border-bottom: 1px solid rgba(0, 0, 0, 0.12); border-left: 1px solid rgba(0, 0, 0, 0.12);">–</td><td style="padding: 0.470903rem 0.770569rem; text-align: center; vertical-align: middle; font-variant-numeric: tabular-nums; font-weight: 400; border-bottom: 1px solid rgba(0, 0, 0, 0.12);">–</td><td style="padding: 0.470903rem 0.770569rem; text-align: center; vertical-align: middle; font-variant-numeric: tabular-nums; font-weight: 400; border-bottom: 1px solid rgba(0, 0, 0, 0.12);">–</td></tr><tr><th scope="row" style="padding: 0.27398rem 0.68495rem; text-align: left; font-size: 0.92em; font-weight: 400; line-height: 1.2; color: rgb(107, 107, 107); background: rgb(242, 242, 242); white-space: nowrap;">Audio</th><td aria-hidden="true" style="padding: 0.27398rem 0.770569rem; background: rgb(242, 242, 242); border-left: 1.5px solid rgba(0, 0, 0, 0.16); border-right: 1.5px solid rgba(0, 0, 0, 0.16);"></td><td aria-hidden="true" style="padding: 0.27398rem 0.770569rem; background: rgb(242, 242, 242);"></td><td aria-hidden="true" style="padding: 0.27398rem 0.770569rem; background: rgb(242, 242, 242);"></td><td aria-hidden="true" style="padding: 0.27398rem 0.770569rem; background: rgb(242, 242, 242);"></td><td aria-hidden="true" style="padding: 0.27398rem 0.770569rem; background: rgb(242, 242, 242);"></td><td aria-hidden="true" style="padding: 0.27398rem 0.770569rem; background: rgb(242, 242, 242);"></td><td aria-hidden="true" style="padding: 0.27398rem 0.770569rem; background: rgb(242, 242, 242);"></td><td aria-hidden="true" style="padding: 0.27398rem 0.770569rem; background: rgb(242, 242, 242); border-left: 1px solid rgba(0, 0, 0, 0.12);"></td><td aria-hidden="true" style="padding: 0.27398rem 0.770569rem; background: rgb(242, 242, 242);"></td><td aria-hidden="true" style="padding: 0.27398rem 0.770569rem; background: rgb(242, 242, 242);"></td></tr><tr><td style="padding: 0.470903rem 0.68495rem; text-align: left; vertical-align: middle; max-width: 188.361px; border-bottom: 1px solid rgba(0, 0, 0, 0.12);"><span style="display: block; line-height: 1.22; white-space: nowrap;">Audio MC</span><span style="display: block; font-size: 0.88em; line-height: 1.25; color: rgb(107, 107, 107); margin-top: 0.18rem; white-space: normal;">Score</span></td><td style="padding: 0.470903rem 0.770569rem; text-align: center; vertical-align: middle; font-variant-numeric: tabular-nums; font-weight: 500; border-bottom: 1px solid rgba(0, 0, 0, 0.12); border-left: 1.5px solid rgba(0, 0, 0, 0.16); border-right: 1.5px solid rgba(0, 0, 0, 0.16);">54.9%</td><td style="padding: 0.470903rem 0.770569rem; text-align: center; vertical-align: middle; font-variant-numeric: tabular-nums; font-weight: 400; border-bottom: 1px solid rgba(0, 0, 0, 0.12);">–</td><td style="padding: 0.470903rem 0.770569rem; text-align: center; vertical-align: middle; font-variant-numeric: tabular-nums; font-weight: 400; border-bottom: 1px solid rgba(0, 0, 0, 0.12);">30.4%</td><td style="padding: 0.470903rem 0.770569rem; text-align: center; vertical-align: middle; font-variant-numeric: tabular-nums; font-weight: 400; border-bottom: 1px solid rgba(0, 0, 0, 0.12);">–</td><td style="padding: 0.470903rem 0.770569rem; text-align: center; vertical-align: middle; font-variant-numeric: tabular-nums; font-weight: 400; border-bottom: 1px solid rgba(0, 0, 0, 0.12);">–</td><td style="padding: 0.470903rem 0.770569rem; text-align: center; vertical-align: middle; font-variant-numeric: tabular-nums; font-weight: 400; border-bottom: 1px solid rgba(0, 0, 0, 0.12);">–</td><td style="padding: 0.470903rem 0.770569rem; text-align: center; vertical-align: middle; font-variant-numeric: tabular-nums; font-weight: 500; background: rgb(251, 236, 191); border-bottom: 1px solid rgba(0, 0, 0, 0.12);">56.6%</td><td style="padding: 0.470903rem 0.770569rem; text-align: center; vertical-align: middle; font-variant-numeric: tabular-nums; font-weight: 400; border-bottom: 1px solid rgba(0, 0, 0, 0.12); border-left: 1px solid rgba(0, 0, 0, 0.12);">–</td><td style="padding: 0.470903rem 0.770569rem; text-align: center; vertical-align: middle; font-variant-numeric: tabular-nums; font-weight: 400; border-bottom: 1px solid rgba(0, 0, 0, 0.12);">33.6%</td><td style="padding: 0.470903rem 0.770569rem; text-align: center; vertical-align: middle; font-variant-numeric: tabular-nums; font-weight: 400; border-bottom: 1px solid rgba(0, 0, 0, 0.12);">–</td></tr><tr><td style="padding: 0.470903rem 0.68495rem; text-align: left; vertical-align: middle; max-width: 188.361px; border-bottom: 1px solid rgba(0, 0, 0, 0.12);"><span style="display: block; line-height: 1.22; white-space: nowrap;">MMAU</span><span style="display: block; font-size: 0.88em; line-height: 1.25; color: rgb(107, 107, 107); margin-top: 0.18rem; white-space: normal;">Score</span></td><td style="padding: 0.470903rem 0.770569rem; text-align: center; vertical-align: middle; font-variant-numeric: tabular-nums; font-weight: 500; border-bottom: 1px solid rgba(0, 0, 0, 0.12); border-left: 1.5px solid rgba(0, 0, 0, 0.16); border-right: 1.5px solid rgba(0, 0, 0, 0.16);">77.0%</td><td style="padding: 0.470903rem 0.770569rem; text-align: center; vertical-align: middle; font-variant-numeric: tabular-nums; font-weight: 400; border-bottom: 1px solid rgba(0, 0, 0, 0.12);">–</td><td style="padding: 0.470903rem 0.770569rem; text-align: center; vertical-align: middle; font-variant-numeric: tabular-nums; font-weight: 400; border-bottom: 1px solid rgba(0, 0, 0, 0.12);">73.6%</td><td style="padding: 0.470903rem 0.770569rem; text-align: center; vertical-align: middle; font-variant-numeric: tabular-nums; font-weight: 400; border-bottom: 1px solid rgba(0, 0, 0, 0.12);">–</td><td style="padding: 0.470903rem 0.770569rem; text-align: center; vertical-align: middle; font-variant-numeric: tabular-nums; font-weight: 400; border-bottom: 1px solid rgba(0, 0, 0, 0.12);">–</td><td style="padding: 0.470903rem 0.770569rem; text-align: center; vertical-align: middle; font-variant-numeric: tabular-nums; font-weight: 400; border-bottom: 1px solid rgba(0, 0, 0, 0.12);">–</td><td style="padding: 0.470903rem 0.770569rem; text-align: center; vertical-align: middle; font-variant-numeric: tabular-nums; font-weight: 500; background: rgb(251, 236, 191); border-bottom: 1px solid rgba(0, 0, 0, 0.12);">77.2%</td><td style="padding: 0.470903rem 0.770569rem; text-align: center; vertical-align: middle; font-variant-numeric: tabular-nums; font-weight: 400; border-bottom: 1px solid rgba(0, 0, 0, 0.12); border-left: 1px solid rgba(0, 0, 0, 0.12);">–</td><td style="padding: 0.470903rem 0.770569rem; text-align: center; vertical-align: middle; font-variant-numeric: tabular-nums; font-weight: 400; border-bottom: 1px solid rgba(0, 0, 0, 0.12);">75.2%</td><td style="padding: 0.470903rem 0.770569rem; text-align: center; vertical-align: middle; font-variant-numeric: tabular-nums; font-weight: 400; border-bottom: 1px solid rgba(0, 0, 0, 0.12);">–</td></tr><tr><td style="padding: 0.470903rem 0.68495rem; text-align: left; vertical-align: middle; max-width: 188.361px; border-bottom-width: medium; border-bottom-style: none; border-bottom-color: currentcolor;"><span style="display: block; line-height: 1.22; white-space: nowrap;">VoiceBench</span><span style="display: block; font-size: 0.88em; line-height: 1.25; color: rgb(107, 107, 107); margin-top: 0.18rem; white-space: normal;">Score</span></td><td style="padding: 0.470903rem 0.770569rem; text-align: center; vertical-align: middle; font-variant-numeric: tabular-nums; font-weight: 500; border-bottom: 1.5px solid rgba(0, 0, 0, 0.16); border-left: 1.5px solid rgba(0, 0, 0, 0.16); border-right: 1.5px solid rgba(0, 0, 0, 0.16); border-bottom-left-radius: 0.55rem; border-bottom-right-radius: 0.55rem;">90.1%</td><td style="padding: 0.470903rem 0.770569rem; text-align: center; vertical-align: middle; font-variant-numeric: tabular-nums; font-weight: 400; border-bottom-width: medium; border-bottom-style: none; border-bottom-color: currentcolor;">–</td><td style="padding: 0.470903rem 0.770569rem; text-align: center; vertical-align: middle; font-variant-numeric: tabular-nums; font-weight: 400; border-bottom-width: medium; border-bottom-style: none; border-bottom-color: currentcolor;">86.4%</td><td style="padding: 0.470903rem 0.770569rem; text-align: center; vertical-align: middle; font-variant-numeric: tabular-nums; font-weight: 400; border-bottom-width: medium; border-bottom-style: none; border-bottom-color: currentcolor;">–</td><td style="padding: 0.470903rem 0.770569rem; text-align: center; vertical-align: middle; font-variant-numeric: tabular-nums; font-weight: 400; border-bottom-width: medium; border-bottom-style: none; border-bottom-color: currentcolor;">–</td><td style="padding: 0.470903rem 0.770569rem; text-align: center; vertical-align: middle; font-variant-numeric: tabular-nums; font-weight: 400; border-bottom-width: medium; border-bottom-style: none; border-bottom-color: currentcolor;">–</td><td style="padding: 0.470903rem 0.770569rem; text-align: center; vertical-align: middle; font-variant-numeric: tabular-nums; font-weight: 500; background: rgb(251, 236, 191); border-bottom-width: medium; border-bottom-style: none; border-bottom-color: currentcolor;">91.4%</td><td style="padding: 0.470903rem 0.770569rem; text-align: center; vertical-align: middle; font-variant-numeric: tabular-nums; font-weight: 400; border-bottom-width: medium; border-bottom-style: none; border-bottom-color: currentcolor; border-left: 1px solid rgba(0, 0, 0, 0.12);">–</td><td style="padding: 0.470903rem 0.770569rem; text-align: center; vertical-align: middle; font-variant-numeric: tabular-nums; font-weight: 400; border-bottom-width: medium; border-bottom-style: none; border-bottom-color: currentcolor;">85.9%</td><td style="padding: 0.470903rem 0.770569rem; text-align: center; vertical-align: middle; font-variant-numeric: tabular-nums; font-weight: 400; border-bottom-width: medium; border-bottom-style: none; border-bottom-color: currentcolor;">–</td></tr></tbody></table>

6. Safety

We conducted safety evaluations ahead of release, spanning both everyday human-AI interaction and dangerous-capability testing. Because Inkling-Small is multimodal, we paid attention to whether safety behavior held consistently across text, audio, and image inputs. We applied mitigations to reduce risks before release.

For everyday interaction, we evaluated sycophancy, harmful manipulation, and psychological-harm patterns like parasocial dependency and validation of delusional reasoning, including through multi-turn, open-ended external red-teaming designed to surface issues that only emerge over longer conversations. We also assessed whether the model refuses genuinely harmful requests without over-refusing benign ones. For CBRN and cyber, we assessed knowledge and procedural uplift through internal evaluations, external testing, and refusal-suppressed variants intended to estimate latent capability with safeguards removed. For loss of control, we evaluated agentic capability, strategic deception, and sabotage potential, benchmarked against public frontier models, and found the model materially below frontier capabilities.

Across all areas, we concluded that Inkling-Small did not present risk of material uplift beyond what's already available in the open-weight ecosystem.

The residual risks identified in our evaluations — specifically, Inkling-Small’s occasional tendency to comply with role-play and indirectly framed prompts concerning harmful topics — are consistent with what you would see from any open-weight model, and are best addressed with defense-in-depth rather than relying on the model's refusals alone. Common downstream moderation tools, such as Llama Guard, are compatible with Inkling-Small and can be layered around the model to catch jailbreak attempts, filter unsafe outputs, and enforce use-case-specific policies. We would encourage treating this kind of input/output classification as a part of your deployment stack, especially for consumer-facing or high-traffic applications where adversarial prompting is more likely.

7. Bias, risks and limitations

Inkling-Small may exhibit general limitations common to foundation models, including hallucination (generating plausible but factually incorrect or unsupported content), occasional failures to follow instructions precisely, and degraded performance in long multi-turn conversations. As with other large-scale models trained on web-derived and synthetic data, Inkling-Small may reflect biases present in its training data, including demographic, cultural, or linguistic biases, and may perform unevenly across languages, dialects, or subject domains that were less represented during training.

Inkling-Small's knowledge is limited to information available as of its training cutoff, and it may not reflect events, developments, or changes that occurred afterward.

We recommend that downstream developers and deployers apply appropriate human oversight and review for outputs used in high-stakes or safety-critical contexts, rather than relying on Inkling-Small's outputs without verification.

  • Conduct their own evaluation of Inkling-Small's performance, safety, and fairness for their specific use case, language, and population prior to deployment, particularly for applications involving vulnerable groups.
  • Implement additional safeguards – such as content filtering, rate limiting, and monitoring – at the application layer, especially for open deployment contexts where Inkling-Small's built-in mitigations may not be sufficient on their own.
  • Avoid deploying Inkling-Small in domains such as medical, legal, or safety-critical decision-making without additional fine-tuning, domain-specific validation, and human oversight

8. Legal

Training Data Documentation

Run unsloth/Inkling-Small-GGUF with guIDE

Download guIDE — the AI-native code editor with local LLM inference and 69 built-in tools.

Download guIDE → · Browse 524k+ models · Compare models

Source: Hugging Face · Compare models