IFM/Jais-3-32B-GGUF overview
Jais 3 32B GGUF NOTE This repository contains GGUF versions of inception42/Jais 3 32B https://huggingface.co/inception42/Jais 3 32B for use with llama.cpp . Mu…
Runs locally from ~19.63 GB disk (24 GB VRAM class GPUs with llama.cpp / guIDE).
Repository Files & Downloads
| File | Type | Quantization | Size | Link |
|---|---|---|---|---|
| Jais-3-32B-BF16.gguf | GGUF | BF16 | 64.79 GB | Download |
| Jais-3-32B-Q4_K_M.gguf | GGUF | Q4_K_M | 19.63 GB | Download |
| Jais-3-32B-Q5_0.gguf | GGUF | Q5_0 | 22.44 GB | Download |
| Jais-3-32B-Q5_K_M.gguf | GGUF | Q5_K_M | 23.00 GB | Download |
| Jais-3-32B-Q6_K.gguf | GGUF | Q6_K | 26.58 GB | Download |
| Jais-3-32B-Q8_0.gguf | GGUF | Q8_0 | 34.43 GB | Download |
Model Details
| Model ID | IFM/Jais-3-32B-GGUF |
|---|---|
| Author | IFM |
| Pipeline | text-generation |
| License | apache-2.0 |
| Base model | inception42/Jais-3-32B |
| Last modified | 2026-10-16T08:21:32.000Z |
Model README
---
pipeline_tag: text-generation
library_name: transformers
model_name: Jais-3-32B
language:
- ar
- en
tags:
- gguf
- llama.cpp
- jais-3
- 32B
- dense
- open-weights
- ifm
base_model:
- inception42/Jais-3-32B
license: apache-2.0
---
Jais-3-32B-GGUF
> [!NOTE]
> This repository contains GGUF versions of inception42/Jais-3-32B for use with llama.cpp.
>
> Multiple precision and quantization variants are available: BF16, Q8_0, Q6_K, Q5_K_M, Q5_0, Q4_K_M.
> [!WARNING]
> Deployment notes: K2 Horizon architecture support is merged into llama.cpp
> (ggml-org/llama.cpp#29535). Use a recent llama.cpp build,
> build it yourself from master, or wait for the next official llama.cpp release. Start llama-server with --jinja so that reasoning and tool calls are parsed.
Jais-3-32B is the large dense member of the Jais-3 family: a 32B-class decoder-only model with a 512K context window.
> [!TIP]
> Other formats are available in the IFM/Jais-3 collection:
> - Quantization: IFM/Jais-3-32B-FP8
> - MLX for Apple silicon:
<p align="center">
<a href="https://huggingface.co/IFM/Jais-3-32B-GGUF/resolve/main/assets/jais-3-32b-benchmarks.png" target="_blank">
<img src="assets/jais-3-32b-benchmarks.png" alt="Jais-3-32B benchmark results" width="100%">
</a>
</p>
Benchmark Results
<!-- TABLE:START -->
<div style="font-family:-apple-system,BlinkMacSystemFont,'Segoe UI',Roboto,sans-serif;margin:0 auto;padding:8px 0 16px;overflow-x:auto"><table style="display:table;width:100%;table-layout:fixed;border-collapse:collapse;font-size:12px;margin:0"><thead><tr><th style="width:23%;border-bottom:none"></th><th style="border-bottom:none"></th><th colspan="5" style="padding:6px 4px 2px;text-align:center;font-size:11px;font-weight:600;letter-spacing:0.04em;text-transform:uppercase;opacity:0.65;border-bottom:1px solid rgba(128,128,128,0.25)">Reference models</th></tr><tr><th style="padding:10px 6px;text-align:left;border-bottom:2px solid #0b9573"></th><th style="padding:10px 3px;text-align:center;font-weight:600;border-bottom:2px solid #0b9573;font-size:12.5px;line-height:1.2;width:12.80%;overflow-wrap:anywhere;background:rgba(11,149,115,0.08);">Jais-3-32B</th><th style="padding:10px 3px;text-align:center;font-weight:600;border-bottom:2px solid #0b9573;font-size:12.5px;line-height:1.2;width:12.80%;overflow-wrap:anywhere;">Falcon-H1-34B-Instruct</th><th style="padding:10px 3px;text-align:center;font-weight:600;border-bottom:2px solid #0b9573;font-size:12.5px;line-height:1.2;width:12.80%;overflow-wrap:anywhere;">Gemma-4-31B-it</th><th style="padding:10px 3px;text-align:center;font-weight:600;border-bottom:2px solid #0b9573;font-size:12.5px;line-height:1.2;width:12.80%;overflow-wrap:anywhere;">Muse-Glimmer-30B</th><th style="padding:10px 3px;text-align:center;font-weight:600;border-bottom:2px solid #0b9573;font-size:12.5px;line-height:1.2;width:12.80%;overflow-wrap:anywhere;">Qwen3.8-27B</th><th style="padding:10px 3px;text-align:center;font-weight:600;border-bottom:2px solid #0b9573;font-size:12.5px;line-height:1.2;width:12.80%;overflow-wrap:anywhere;">Fanar-2-27B</th></tr></thead><tbody><tr><td style="padding:7px 4px 7px 10px;border-bottom:1px solid rgba(128,128,128,0.15);vertical-align:middle;font-size:12.5px;font-weight:600"># Params</td><td style="padding:6px 2px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15);vertical-align:middle;font-size:12.5px;line-height:1.2;background:rgba(11,149,115,0.08);">32B</td><td style="padding:6px 2px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15);vertical-align:middle;font-size:12.5px;line-height:1.2;">34B</td><td style="padding:6px 2px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15);vertical-align:middle;font-size:12.5px;line-height:1.2;">31B</td><td style="padding:6px 2px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15);vertical-align:middle;font-size:12.5px;line-height:1.2;">30B</td><td style="padding:6px 2px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15);vertical-align:middle;font-size:12.5px;line-height:1.2;">27B</td><td style="padding:6px 2px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15);vertical-align:middle;font-size:12.5px;line-height:1.2;">27B</td></tr><tr><td style="padding:7px 4px 7px 10px;border-bottom:1px solid rgba(128,128,128,0.15);vertical-align:middle;font-size:12.5px;font-weight:600"># Activated params</td><td style="padding:6px 2px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15);vertical-align:middle;font-size:12.5px;line-height:1.2;background:rgba(11,149,115,0.08);">32B</td><td style="padding:6px 2px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15);vertical-align:middle;font-size:12.5px;line-height:1.2;">34B</td><td style="padding:6px 2px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15);vertical-align:middle;font-size:12.5px;line-height:1.2;">31B</td><td style="padding:6px 2px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15);vertical-align:middle;font-size:12.5px;line-height:1.2;">30B</td><td style="padding:6px 2px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15);vertical-align:middle;font-size:12.5px;line-height:1.2;">27B</td><td style="padding:6px 2px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15);vertical-align:middle;font-size:12.5px;line-height:1.2;">27B</td></tr><tr><td style="padding:7px 4px 7px 10px;border-bottom:1px solid rgba(128,128,128,0.15);vertical-align:middle;font-size:12.5px;font-weight:600">Architecture</td><td style="padding:6px 2px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15);vertical-align:middle;font-size:12.5px;line-height:1.2;background:rgba(11,149,115,0.08);">Dense</td><td style="padding:6px 2px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15);vertical-align:middle;font-size:12.5px;line-height:1.2;">Dense</td><td style="padding:6px 2px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15);vertical-align:middle;font-size:12.5px;line-height:1.2;">Dense</td><td style="padding:6px 2px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15);vertical-align:middle;font-size:12.5px;line-height:1.2;">Dense</td><td style="padding:6px 2px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15);vertical-align:middle;font-size:12.5px;line-height:1.2;">Dense</td><td style="padding:6px 2px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15);vertical-align:middle;font-size:12.5px;line-height:1.2;">Dense</td></tr><tr><td colspan="7" style="padding:9px 10px 7px;font-weight:700;font-size:11px;letter-spacing:0.05em;text-transform:uppercase;border-bottom:1px solid rgba(11,149,115,0.4);background:rgba(11,149,115,0.22)">Open-ended Generation</td></tr><tr><td colspan="7" style="padding:6px 10px;font-weight:600;font-size:12.5px;border-bottom:1px solid rgba(11,149,115,0.25);background:rgba(11,149,115,0.06)">AraGen</td></tr><tr><td style="padding:6px 4px 6px 10px;border-bottom:1px solid rgba(128,128,128,0.15);vertical-align:middle"><div style="font-size:12.5px;font-weight:600;line-height:1.2;color:inherit">AraGen v3 (3C3H)</div><div style="margin-top:2px;font-size:10px;opacity:0.65">09-2025</div></td><td style="padding:6px 2px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15);vertical-align:middle;font-size:12.5px;line-height:1.2;background:rgba(11,149,115,0.08);">71.0</td><td style="padding:6px 2px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15);vertical-align:middle;font-size:12.5px;line-height:1.2;">45.0</td><td style="padding:6px 2px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15);vertical-align:middle;font-size:12.5px;line-height:1.2;">73.4</td><td style="padding:6px 2px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15);vertical-align:middle;font-size:12.5px;line-height:1.2;"><strong>75.6</strong></td><td style="padding:6px 2px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15);vertical-align:middle;font-size:12.5px;line-height:1.2;">66.7</td><td style="padding:6px 2px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15);vertical-align:middle;font-size:12.5px;line-height:1.2;">55.9</td></tr><tr><td data-detail="detail" style="padding:5px 4px 5px 24px;border-bottom:1px solid rgba(128,128,128,0.15);vertical-align:middle"><div style="font-size:11.5px;font-weight:400;line-height:1.2;color:inherit">Correctness</div></td><td style="padding:5px 2px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15);vertical-align:middle;font-size:11.5px;line-height:1.2;background:rgba(11,149,115,0.08);">81.0</td><td style="padding:5px 2px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15);vertical-align:middle;font-size:11.5px;line-height:1.2;">53.2</td><td style="padding:5px 2px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15);vertical-align:middle;font-size:11.5px;line-height:1.2;">85.4</td><td style="padding:5px 2px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15);vertical-align:middle;font-size:11.5px;line-height:1.2;"><strong>87.7</strong></td><td style="padding:5px 2px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15);vertical-align:middle;font-size:11.5px;line-height:1.2;">77.1</td><td style="padding:5px 2px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15);vertical-align:middle;font-size:11.5px;line-height:1.2;">65.7</td></tr><tr><td data-detail="detail" style="padding:5px 4px 5px 24px;border-bottom:1px solid rgba(128,128,128,0.15);vertical-align:middle"><div style="font-size:11.5px;font-weight:400;line-height:1.2;color:inherit">Completeness</div></td><td style="padding:5px 2px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15);vertical-align:middle;font-size:11.5px;line-height:1.2;background:rgba(11,149,115,0.08);">80.3</td><td style="padding:5px 2px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15);vertical-align:middle;font-size:11.5px;line-height:1.2;">51.0</td><td style="padding:5px 2px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15);vertical-align:middle;font-size:11.5px;line-height:1.2;">84.9</td><td style="padding:5px 2px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15);vertical-align:middle;font-size:11.5px;line-height:1.2;"><strong>87.0</strong></td><td style="padding:5px 2px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15);vertical-align:middle;font-size:11.5px;line-height:1.2;">76.2</td><td style="padding:5px 2px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15);vertical-align:middle;font-size:11.5px;line-height:1.2;">63.5</td></tr><tr><td data-detail="detail" style="padding:5px 4px 5px 24px;border-bottom:1px solid rgba(128,128,128,0.15);vertical-align:middle"><div style="font-size:11.5px;font-weight:400;line-height:1.2;color:inherit">Conciseness</div></td><td style="padding:5px 2px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15);vertical-align:middle;font-size:11.5px;line-height:1.2;background:rgba(11,149,115,0.08);"><strong>28.1</strong></td><td style="padding:5px 2px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15);vertical-align:middle;font-size:11.5px;line-height:1.2;">19.7</td><td style="padding:5px 2px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15);vertical-align:middle;font-size:11.5px;line-height:1.2;">21.1</td><td style="padding:5px 2px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15);vertical-align:middle;font-size:11.5px;line-height:1.2;">23.0</td><td style="padding:5px 2px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15);vertical-align:middle;font-size:11.5px;line-height:1.2;">23.9</td><td style="padding:5px 2px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15);vertical-align:middle;font-size:11.5px;line-height:1.2;">21.6</td></tr><tr><td data-detail="detail" style="padding:5px 4px 5px 24px;border-bottom:1px solid rgba(128,128,128,0.15);vertical-align:middle"><div style="font-size:11.5px;font-weight:400;line-height:1.2;color:inherit">Helpfulness</div></td><td style="padding:5px 2px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15);vertical-align:middle;font-size:11.5px;line-height:1.2;background:rgba(11,149,115,0.08);">76.4</td><td style="padding:5px 2px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15);vertical-align:middle;font-size:11.5px;line-height:1.2;">45.4</td><td style="padding:5px 2px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15);vertical-align:middle;font-size:11.5px;line-height:1.2;">79.7</td><td style="padding:5px 2px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15);vertical-align:middle;font-size:11.5px;line-height:1.2;"><strong>81.2</strong></td><td style="padding:5px 2px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15);vertical-align:middle;font-size:11.5px;line-height:1.2;">71.5</td><td style="padding:5px 2px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15);vertical-align:middle;font-size:11.5px;line-height:1.2;">59.0</td></tr><tr><td data-detail="detail" style="padding:5px 4px 5px 24px;border-bottom:1px solid rgba(128,128,128,0.15);vertical-align:middle"><div style="font-size:11.5px;font-weight:400;line-height:1.2;color:inherit">Honesty</div></td><td style="padding:5px 2px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15);vertical-align:middle;font-size:11.5px;line-height:1.2;background:rgba(11,149,115,0.08);">79.9</td><td style="padding:5px 2px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15);vertical-align:middle;font-size:11.5px;line-height:1.2;">49.0</td><td style="padding:5px 2px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15);vertical-align:middle;font-size:11.5px;line-height:1.2;">84.4</td><td style="padding:5px 2px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15);vertical-align:middle;font-size:11.5px;line-height:1.2;"><strong>86.7</strong></td><td style="padding:5px 2px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15);vertical-align:middle;font-size:11.5px;line-height:1.2;">74.7</td><td style="padding:5px 2px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15);vertical-align:middle;font-size:11.5px;line-height:1.2;">61.3</td></tr><tr><td data-detail="detail" style="padding:5px 4px 5px 24px;border-bottom:1px solid rgba(128,128,128,0.15);vertical-align:middle"><div style="font-size:11.5px;font-weight:400;line-height:1.2;color:inherit">Harmlessness</div></td><td style="padding:5px 2px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15);vertical-align:middle;font-size:11.5px;line-height:1.2;background:rgba(11,149,115,0.08);">80.3</td><td style="padding:5px 2px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15);vertical-align:middle;font-size:11.5px;line-height:1.2;">51.4</td><td style="padding:5px 2px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15);vertical-align:middle;font-size:11.5px;line-height:1.2;">84.9</td><td style="padding:5px 2px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15);vertical-align:middle;font-size:11.5px;line-height:1.2;"><strong>87.7</strong></td><td style="padding:5px 2px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15);vertical-align:middle;font-size:11.5px;line-height:1.2;">76.5</td><td style="padding:5px 2px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15);vertical-align:middle;font-size:11.5px;line-height:1.2;">64.4</td></tr><tr><td colspan="7" style="padding:9px 10px 7px;font-weight:700;font-size:11px;letter-spacing:0.05em;text-transform:uppercase;border-bottom:1px solid rgba(11,149,115,0.4);background:rgba(11,149,115,0.22)">Knowledge & Reasoning</td></tr><tr><td colspan="7" style="padding:6px 10px;font-weight:600;font-size:12.5px;border-bottom:1px solid rgba(11,149,115,0.25);background:rgba(11,149,115,0.06)">General Knowledge & Comprehension</td></tr><tr><td style="padding:6px 4px 6px 10px;border-bottom:1px solid rgba(128,128,128,0.15);vertical-align:middle"><div style="font-size:12.5px;font-weight:600;line-height:1.2;color:inherit">Arabic MMLU</div><div style="margin-top:2px;font-size:10px;opacity:0.65">Accuracy</div></td><td style="padding:6px 2px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15);vertical-align:middle;font-size:12.5px;line-height:1.2;background:rgba(11,149,115,0.08);">88.6</td><td style="padding:6px 2px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15);vertical-align:middle;font-size:12.5px;line-height:1.2;">73.7</td><td style="padding:6px 2px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15);vertical-align:middle;font-size:12.5px;line-height:1.2;"><strong>89.5</strong></td><td style="padding:6px 2px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15);vertical-align:middle;font-size:12.5px;line-height:1.2;">87.0</td><td style="padding:6px 2px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15);vertical-align:middle;font-size:12.5px;line-height:1.2;">85.8</td><td style="padding:6px 2px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15);vertical-align:middle;font-size:12.5px;line-height:1.2;">66.3</td></tr><tr><td style="padding:6px 4px 6px 10px;border-bottom:1px solid rgba(128,128,128,0.15);vertical-align:middle"><div style="font-size:12.5px;font-weight:600;line-height:1.2;color:inherit">Belebele</div><div style="margin-top:2px;font-size:10px;opacity:0.65">Accuracy</div></td><td style="padding:6px 2px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15);vertical-align:middle;font-size:12.5px;line-height:1.2;background:rgba(11,149,115,0.08);">95.0</td><td style="padding:6px 2px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15);vertical-align:middle;font-size:12.5px;line-height:1.2;">86.6</td><td style="padding:6px 2px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15);vertical-align:middle;font-size:12.5px;line-height:1.2;"><strong>95.9</strong></td><td style="padding:6px 2px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15);vertical-align:middle;font-size:12.5px;line-height:1.2;">94.3</td><td style="padding:6px 2px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15);vertical-align:middle;font-size:12.5px;line-height:1.2;">94.4</td><td style="padding:6px 2px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15);vertical-align:middle;font-size:12.5px;line-height:1.2;">61.8</td></tr><tr><td colspan="7" style="padding:6px 10px;font-weight:600;font-size:12.5px;border-bottom:1px solid rgba(11,149,115,0.25);background:rgba(11,149,115,0.06)">STEM & Math</td></tr><tr><td style="padding:6px 4px 6px 10px;border-bottom:1px solid rgba(128,128,128,0.15);vertical-align:middle"><div style="font-size:12.5px;font-weight:600;line-height:1.2;color:inherit">AraSTEM</div><div style="margin-top:2px;font-size:10px;opacity:0.65">Accuracy</div></td><td style="padding:6px 2px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15);vertical-align:middle;font-size:12.5px;line-height:1.2;background:rgba(11,149,115,0.08);">95.2</td><td style="padding:6px 2px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15);vertical-align:middle;font-size:12.5px;line-height:1.2;">85.5</td><td style="padding:6px 2px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15);vertical-align:middle;font-size:12.5px;line-height:1.2;"><strong>96.3</strong></td><td style="padding:6px 2px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15);vertical-align:middle;font-size:12.5px;line-height:1.2;">94.7</td><td style="padding:6px 2px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15);vertical-align:middle;font-size:12.5px;line-height:1.2;">95.3</td><td style="padding:6px 2px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15);vertical-align:middle;font-size:12.5px;line-height:1.2;">42.4</td></tr><tr><td style="padding:6px 4px 6px 10px;border-bottom:1px solid rgba(128,128,128,0.15);vertical-align:middle"><div style="font-size:12.5px;font-weight:600;line-height:1.2;color:inherit">Arabic GSM8K</div><div style="margin-top:2px;font-size:10px;opacity:0.65">Accuracy</div></td><td style="padding:6px 2px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15);vertical-align:middle;font-size:12.5px;line-height:1.2;background:rgba(11,149,115,0.08);">94.3</td><td style="padding:6px 2px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15);vertical-align:middle;font-size:12.5px;line-height:1.2;">90.2</td><td style="padding:6px 2px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15);vertical-align:middle;font-size:12.5px;line-height:1.2;">93.7</td><td style="padding:6px 2px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15);vertical-align:middle;font-size:12.5px;line-height:1.2;"><strong>95.2</strong></td><td style="padding:6px 2px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15);vertical-align:middle;font-size:12.5px;line-height:1.2;">93.2</td><td style="padding:6px 2px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15);vertical-align:middle;font-size:12.5px;line-height:1.2;">87.7</td></tr><tr><td style="padding:6px 4px 6px 10px;border-bottom:1px solid rgba(128,128,128,0.15);vertical-align:middle"><div style="font-size:12.5px;font-weight:600;line-height:1.2;color:inherit">GATmath</div><div style="margin-top:2px;font-size:10px;opacity:0.65">Accuracy</div></td><td style="padding:6px 2px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15);vertical-align:middle;font-size:12.5px;line-height:1.2;background:rgba(11,149,115,0.08);">98.5</td><td style="padding:6px 2px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15);vertical-align:middle;font-size:12.5px;line-height:1.2;">63.4</td><td style="padding:6px 2px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15);vertical-align:middle;font-size:12.5px;line-height:1.2;"><strong>98.6</strong></td><td style="padding:6px 2px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15);vertical-align:middle;font-size:12.5px;line-height:1.2;">98.5</td><td style="padding:6px 2px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15);vertical-align:middle;font-size:12.5px;line-height:1.2;">98.4</td><td style="padding:6px 2px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15);vertical-align:middle;font-size:12.5px;line-height:1.2;">87.8</td></tr><tr><td colspan="7" style="padding:6px 10px;font-weight:600;font-size:12.5px;border-bottom:1px solid rgba(11,149,115,0.25);background:rgba(11,149,115,0.06)">Professional Domains</td></tr><tr><td style="padding:6px 4px 6px 10px;border-bottom:1px solid rgba(128,128,128,0.15);vertical-align:middle"><div style="font-size:12.5px;font-weight:600;line-height:1.2;color:inherit">MedAraBench</div><div style="margin-top:2px;font-size:10px;opacity:0.65">Accuracy</div></td><td style="padding:6px 2px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15);vertical-align:middle;font-size:12.5px;line-height:1.2;background:rgba(11,149,115,0.08);">87.0</td><td style="padding:6px 2px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15);vertical-align:middle;font-size:12.5px;line-height:1.2;">60.7</td><td style="padding:6px 2px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15);vertical-align:middle;font-size:12.5px;line-height:1.2;"><strong>88.8</strong></td><td style="padding:6px 2px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15);vertical-align:middle;font-size:12.5px;line-height:1.2;">86.1</td><td style="padding:6px 2px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15);vertical-align:middle;font-size:12.5px;line-height:1.2;">87.3</td><td style="padding:6px 2px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15);vertical-align:middle;font-size:12.5px;line-height:1.2;">50.9</td></tr><tr><td style="padding:6px 4px 6px 10px;border-bottom:1px solid rgba(128,128,128,0.15);vertical-align:middle"><div style="font-size:12.5px;font-weight:600;line-height:1.2;color:inherit">Arabic Legal (HELM)</div><div style="margin-top:2px;font-size:10px;opacity:0.65">Accuracy</div></td><td style="padding:6px 2px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15);vertical-align:middle;font-size:12.5px;line-height:1.2;background:rgba(11,149,115,0.08);"><strong>73.4</strong></td><td style="padding:6px 2px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15);vertical-align:middle;font-size:12.5px;line-height:1.2;">63.1</td><td style="padding:6px 2px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15);vertical-align:middle;font-size:12.5px;line-height:1.2;">71.1</td><td style="padding:6px 2px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15);vertical-align:middle;font-size:12.5px;line-height:1.2;">73.1</td><td style="padding:6px 2px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15);vertical-align:middle;font-size:12.5px;line-height:1.2;">70.5</td><td style="padding:6px 2px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15);vertical-align:middle;font-size:12.5px;line-height:1.2;">45.7</td></tr><tr><td colspan="7" style="padding:9px 10px 7px;font-weight:700;font-size:11px;letter-spacing:0.05em;text-transform:uppercase;border-bottom:1px solid rgba(11,149,115,0.4);background:rgba(11,149,115,0.22)">Arabic Language & Culture</td></tr><tr><td colspan="7" style="padding:6px 10px;font-weight:600;font-size:12.5px;border-bottom:1px solid rgba(11,149,115,0.25);background:rgba(11,149,115,0.06)">Islamic Knowledge & Arab Culture</td></tr><tr><td style="padding:6px 4px 6px 10px;border-bottom:1px solid rgba(128,128,128,0.15);vertical-align:middle"><div style="font-size:12.5px;font-weight:600;line-height:1.2;color:inherit">IslamicQA</div><div style="margin-top:2px;font-size:10px;opacity:0.65">Accuracy (mean of the 4 below)</div></td><td style="padding:6px 2px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15);vertical-align:middle;font-size:12.5px;line-height:1.2;background:rgba(11,149,115,0.08);">88.7</td><td style="padding:6px 2px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15);vertical-align:middle;font-size:12.5px;line-height:1.2;">71.1</td><td style="padding:6px 2px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15);vertical-align:middle;font-size:12.5px;line-height:1.2;"><strong>89.7</strong></td><td style="padding:6px 2px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15);vertical-align:middle;font-size:12.5px;line-height:1.2;">83.7</td><td style="padding:6px 2px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15);vertical-align:middle;font-size:12.5px;line-height:1.2;">77.1</td><td style="padding:6px 2px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15);vertical-align:middle;font-size:12.5px;line-height:1.2;">52.0</td></tr><tr><td data-detail="detail" style="padding:5px 4px 5px 24px;border-bottom:1px solid rgba(128,128,128,0.15);vertical-align:middle"><div style="font-size:11.5px;font-weight:400;line-height:1.2;color:inherit">PaLM-X 2025-2</div><div style="margin-top:2px;font-size:10px;opacity:0.65">Accuracy</div></td><td style="padding:5px 2px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15);vertical-align:middle;font-size:11.5px;line-height:1.2;background:rgba(11,149,115,0.08);"><strong>94.6</strong></td><td style="padding:5px 2px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15);vertical-align:middle;font-size:11.5px;line-height:1.2;">84.7</td><td style="padding:5px 2px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15);vertical-align:middle;font-size:11.5px;line-height:1.2;">94.5</td><td style="padding:5px 2px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15);vertical-align:middle;font-size:11.5px;line-height:1.2;">92.6</td><td style="padding:5px 2px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15);vertical-align:middle;font-size:11.5px;line-height:1.2;">90.8</td><td style="padding:5px 2px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15);vertical-align:middle;font-size:11.5px;line-height:1.2;">69.3</td></tr><tr><td data-detail="detail" style="padding:5px 4px 5px 24px;border-bottom:1px solid rgba(128,128,128,0.15);vertical-align:middle"><div style="font-size:11.5px;font-weight:400;line-height:1.2;color:inherit">QIAS-1</div><div style="margin-top:2px;font-size:10px;opacity:0.65">Accuracy</div></td><td style="padding:5px 2px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15);vertical-align:middle;font-size:11.5px;line-height:1.2;background:rgba(11,149,115,0.08);"><strong>95.9</strong></td><td style="padding:5px 2px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15);vertical-align:middle;font-size:11.5px;line-height:1.2;">56.2</td><td style="padding:5px 2px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15);vertical-align:middle;font-size:11.5px;line-height:1.2;">93.2</td><td style="padding:5px 2px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15);vertical-align:middle;font-size:11.5px;line-height:1.2;">87.4</td><td style="padding:5px 2px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15);vertical-align:middle;font-size:11.5px;line-height:1.2;">81.6</td><td style="padding:5px 2px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15);vertical-align:middle;font-size:11.5px;line-height:1.2;">31.4</td></tr><tr><td data-detail="detail" style="padding:5px 4px 5px 24px;border-bottom:1px solid rgba(128,128,128,0.15);vertical-align:middle"><div style="font-size:11.5px;font-weight:400;line-height:1.2;color:inherit">QIAS-2</div><div style="margin-top:2px;font-size:10px;opacity:0.65">Accuracy</div></td><td style="padding:5px 2px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15);vertical-align:middle;font-size:11.5px;line-height:1.2;background:rgba(11,149,115,0.08);">85.5</td><td style="padding:5px 2px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15);vertical-align:middle;font-size:11.5px;line-height:1.2;">73.4</td><td style="padding:5px 2px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15);vertical-align:middle;font-size:11.5px;line-height:1.2;"><strong>86.9</strong></td><td style="padding:5px 2px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15);vertical-align:middle;font-size:11.5px;line-height:1.2;">83.0</td><td style="padding:5px 2px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15);vertical-align:middle;font-size:11.5px;line-height:1.2;">81.9</td><td style="padding:5px 2px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15);vertical-align:middle;font-size:11.5px;line-height:1.2;">61.8</td></tr><tr><td data-detail="detail" style="padding:5px 4px 5px 24px;border-bottom:1px solid rgba(128,128,128,0.15);vertical-align:middle"><div style="font-size:11.5px;font-weight:400;line-height:1.2;color:inherit">IslamicEval2025-1B</div><div style="margin-top:2px;font-size:10px;opacity:0.65">Accuracy</div></td><td style="padding:5px 2px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15);vertical-align:middle;font-size:11.5px;line-height:1.2;background:rgba(11,149,115,0.08);">78.8</td><td style="padding:5px 2px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15);vertical-align:middle;font-size:11.5px;line-height:1.2;">70.1</td><td style="padding:5px 2px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15);vertical-align:middle;font-size:11.5px;line-height:1.2;"><strong>84.0</strong></td><td style="padding:5px 2px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15);vertical-align:middle;font-size:11.5px;line-height:1.2;">71.9</td><td style="padding:5px 2px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15);vertical-align:middle;font-size:11.5px;line-height:1.2;">54.1</td><td style="padding:5px 2px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15);vertical-align:middle;font-size:11.5px;line-height:1.2;">45.5</td></tr><tr><td data-detail="summary" style="padding:6px 4px 6px 10px;border-bottom:1px solid rgba(128,128,128,0.15);vertical-align:middle"><div style="font-size:12.5px;font-weight:600;line-height:1.2;color:inherit">Arab Culture</div><div style="margin-top:2px;font-size:10px;opacity:0.65">Accuracy (mean of the 3 below)</div></td><td style="padding:6px 2px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15);vertical-align:middle;font-size:12.5px;line-height:1.2;background:rgba(11,149,115,0.08);">88.0</td><td style="padding:6px 2px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15);vertical-align:middle;font-size:12.5px;line-height:1.2;">76.5</td><td style="padding:6px 2px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15);vertical-align:middle;font-size:12.5px;line-height:1.2;"><strong>90.2</strong></td><td style="padding:6px 2px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15);vertical-align:middle;font-size:12.5px;line-height:1.2;">84.6</td><td style="padding:6px 2px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15);vertical-align:middle;font-size:12.5px;line-height:1.2;">81.0</td><td style="padding:6px 2px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15);vertical-align:middle;font-size:12.5px;line-height:1.2;">41.4</td></tr><tr><td style="padding:5px 4px 5px 24px;border-bottom:1px solid rgba(128,128,128,0.15);vertical-align:middle"><div style="font-size:11.5px;font-weight:400;line-height:1.2;color:inherit">ArabCulture</div><div style="margin-top:2px;font-size:10px;opacity:0.65">Accuracy</div></td><td style="padding:5px 2px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15);vertical-align:middle;font-size:11.5px;line-height:1.2;background:rgba(11,149,115,0.08);">88.2</td><td style="padding:5px 2px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15);vertical-align:middle;font-size:11.5px;line-height:1.2;">79.7</td><td style="padding:5px 2px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15);vertical-align:middle;font-size:11.5px;line-height:1.2;"><strong>91.4</strong></td><td style="padding:5px 2px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15);vertical-align:middle;font-size:11.5px;line-height:1.2;">86.0</td><td style="padding:5px 2px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15);vertical-align:middle;font-size:11.5px;line-height:1.2;">85.0</td><td style="padding:5px 2px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15);vertical-align:middle;font-size:11.5px;line-height:1.2;">34.2</td></tr><tr><td style="padding:5px 4px 5px 24px;border-bottom:1px solid rgba(128,128,128,0.15);vertical-align:middle"><div style="font-size:11.5px;font-weight:400;line-height:1.2;color:inherit">AraDiCE-Culture</div><div style="margin-top:2px;font-size:10px;opacity:0.65">Accuracy</div></td><td style="padding:5px 2px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15);vertical-align:middle;font-size:11.5px;line-height:1.2;background:rgba(11,149,115,0.08);">88.3</td><td style="padding:5px 2px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15);vertical-align:middle;font-size:11.5px;line-height:1.2;">75.4</td><td style="padding:5px 2px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15);vertical-align:middle;font-size:11.5px;line-height:1.2;"><strong>89.4</strong></td><td style="padding:5px 2px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15);vertical-align:middle;font-size:11.5px;line-height:1.2;">83.2</td><td style="padding:5px 2px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15);vertical-align:middle;font-size:11.5px;line-height:1.2;">77.1</td><td style="padding:5px 2px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15);vertical-align:middle;font-size:11.5px;line-height:1.2;">55.9</td></tr><tr><td style="padding:5px 4px 5px 24px;border-bottom:1px solid rgba(128,128,128,0.15);vertical-align:middle"><div style="font-size:11.5px;font-weight:400;line-height:1.2;color:inherit">Arabic Cuisine^</div><div style="margin-top:2px;font-size:10px;opacity:0.65">Accuracy</div></td><td style="padding:5px 2px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15);vertical-align:middle;font-size:11.5px;line-height:1.2;background:rgba(11,149,115,0.08);">87.4</td><td style="padding:5px 2px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15);vertical-align:middle;font-size:11.5px;line-height:1.2;">74.4</td><td style="padding:5px 2px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15);vertical-align:middle;font-size:11.5px;line-height:1.2;"><strong>89.8</strong></td><td style="padding:5px 2px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15);vertical-align:middle;font-size:11.5px;line-height:1.2;">84.7</td><td style="padding:5px 2px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15);vertical-align:middle;font-size:11.5px;line-height:1.2;">81.0</td><td style="padding:5px 2px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15);vertical-align:middle;font-size:11.5px;line-height:1.2;">34.0</td></tr><tr><td colspan="7" style="padding:6px 10px;font-weight:600;font-size:12.5px;border-bottom:1px solid rgba(11,149,115,0.25);background:rgba(11,149,115,0.06)">Dialects</td></tr><tr><td style="padding:6px 4px 6px 10px;border-bottom:1px solid rgba(128,128,128,0.15);vertical-align:middle"><div style="font-size:12.5px;font-weight:600;line-height:1.2;color:inherit">Dialectal Arabic MMLU</div><div style="margin-top:2px;font-size:10px;opacity:0.65">Accuracy</div></td><td style="padding:6px 2px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15);vertical-align:middle;font-size:12.5px;line-height:1.2;background:rgba(11,149,115,0.08);">88.5</td><td style="padding:6px 2px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15);vertical-align:middle;font-size:12.5px;line-height:1.2;">71.5</td><td style="padding:6px 2px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15);vertical-align:middle;font-size:12.5px;line-height:1.2;"><strong>89.4</strong></td><td style="padding:6px 2px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15);vertical-align:middle;font-size:12.5px;line-height:1.2;">87.0</td><td style="padding:6px 2px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15);vertical-align:middle;font-size:12.5px;line-height:1.2;">87.0</td><td style="padding:6px 2px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15);vertical-align:middle;font-size:12.5px;line-height:1.2;">28.2</td></tr><tr><td style="padding:6px 4px 6px 10px;border-bottom:1px solid rgba(128,128,128,0.15);vertical-align:middle"><div style="font-size:12.5px;font-weight:600;line-height:1.2;color:inherit">Dialect Identification (QADI)</div><div style="margin-top:2px;font-size:10px;opacity:0.65">Accuracy</div></td><td style="padding:6px 2px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15);vertical-align:middle;font-size:12.5px;line-height:1.2;background:rgba(11,149,115,0.08);"><strong>70.6</strong></td><td style="padding:6px 2px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15);vertical-align:middle;font-size:12.5px;line-height:1.2;">50.3</td><td style="padding:6px 2px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15);vertical-align:middle;font-size:12.5px;line-height:1.2;">70.4</td><td style="padding:6px 2px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15);vertical-align:middle;font-size:12.5px;line-height:1.2;">60.6</td><td style="padding:6px 2px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15);vertical-align:middle;font-size:12.5px;line-height:1.2;">51.5</td><td style="padding:6px 2px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15);vertical-align:middle;font-size:12.5px;line-height:1.2;">29.6</td></tr><tr><td style="padding:6px 4px 6px 10px;border-bottom:1px solid rgba(128,128,128,0.15);vertical-align:middle"><div style="font-size:12.5px;font-weight:600;line-height:1.2;color:inherit">Alyah</div><div style="margin-top:2px;font-size:10px;opacity:0.65">Accuracy</div></td><td style="padding:6px 2px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15);vertical-align:middle;font-size:12.5px;line-height:1.2;background:rgba(11,149,115,0.08);">83.0</td><td style="padding:6px 2px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15);vertical-align:middle;font-size:12.5px;line-height:1.2;">71.8</td><td style="padding:6px 2px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15);vertical-align:middle;font-size:12.5px;line-height:1.2;"><strong>88.4</strong></td><td style="padding:6px 2px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15);vertical-align:middle;font-size:12.5px;line-height:1.2;">80.3</td><td style="padding:6px 2px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15);vertical-align:middle;font-size:12.5px;line-height:1.2;">77.7</td><td style="padding:6px 2px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15);vertical-align:middle;font-size:12.5px;line-height:1.2;">36.3</td></tr><tr><td colspan="7" style="padding:6px 10px;font-weight:600;font-size:12.5px;border-bottom:1px solid rgba(11,149,115,0.25);background:rgba(11,149,115,0.06)">Linguistics & Literature</td></tr><tr><td style="padding:6px 4px 6px 10px;border-bottom:1px solid rgba(128,128,128,0.15);vertical-align:middle"><div style="font-size:12.5px;font-weight:600;line-height:1.2;color:inherit">Arabic MMLU with diacritics</div><div style="margin-top:2px;font-size:10px;opacity:0.65">Accuracy</div></td><td style="padding:6px 2px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15);vertical-align:middle;font-size:12.5px;line-height:1.2;background:rgba(11,149,115,0.08);">87.9</td><td style="padding:6px 2px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15);vertical-align:middle;font-size:12.5px;line-height:1.2;">69.1</td><td style="padding:6px 2px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15);vertical-align:middle;font-size:12.5px;line-height:1.2;"><strong>88.9</strong></td><td style="padding:6px 2px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15);vertical-align:middle;font-size:12.5px;line-height:1.2;">86.6</td><td style="padding:6px 2px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15);vertical-align:middle;font-size:12.5px;line-height:1.2;">85.2</td><td style="padding:6px 2px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15);vertical-align:middle;font-size:12.5px;line-height:1.2;">64.2</td></tr><tr><td style="padding:6px 4px 6px 10px;border-bottom:1px solid rgba(128,128,128,0.15);vertical-align:middle"><div style="font-size:12.5px;font-weight:600;line-height:1.2;color:inherit">FannOrFlop-MCQ</div><div style="margin-top:2px;font-size:10px;opacity:0.65">Accuracy</div></td><td style="padding:6px 2px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15);vertical-align:middle;font-size:12.5px;line-height:1.2;background:rgba(11,149,115,0.08);">71.8</td><td style="padding:6px 2px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15);vertical-align:middle;font-size:12.5px;line-height:1.2;">62.4</td><td style="padding:6px 2px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15);vertical-align:middle;font-size:12.5px;line-height:1.2;"><strong>72.6</strong></td><td style="padding:6px 2px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15);vertical-align:middle;font-size:12.5px;line-height:1.2;">68.3</td><td style="padding:6px 2px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15);vertical-align:middle;font-size:12.5px;line-height:1.2;">62.5</td><td style="padding:6px 2px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15);vertical-align:middle;font-size:12.5px;line-height:1.2;">46.4</td></tr><tr><td style="padding:6px 4px 6px 10px;border-bottom:1px solid rgba(128,128,128,0.15);vertical-align:middle"><div style="font-size:12.5px;font-weight:600;line-height:1.2;color:inherit">Arabic Linguistics^</div><div style="margin-top:2px;font-size:10px;opacity:0.65">Accuracy (mean of the 2 below)</div></td><td style="padding:6px 2px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15);vertical-align:middle;font-size:12.5px;line-height:1.2;background:rgba(11,149,115,0.08);">94.3</td><td style="padding:6px 2px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15);vertical-align:middle;font-size:12.5px;line-height:1.2;">57.4</td><td style="padding:6px 2px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15);vertical-align:middle;font-size:12.5px;line-height:1.2;"><strong>96.7</strong></td><td style="padding:6px 2px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15);vertical-align:middle;font-size:12.5px;line-height:1.2;">91.8</td><td style="padding:6px 2px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15);vertical-align:middle;font-size:12.5px;line-height:1.2;">89.7</td><td style="padding:6px 2px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15);vertical-align:middle;font-size:12.5px;line-height:1.2;">39.1</td></tr><tr><td data-detail="detail" style="padding:5px 4px 5px 24px;border-bottom:1px solid rgba(128,128,128,0.15);vertical-align:middle"><div style="font-size:11.5px;font-weight:400;line-height:1.2;color:inherit">Diacritization</div><div style="margin-top:2px;font-size:10px;opacity:0.65">Accuracy</div></td><td style="padding:5px 2px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15);vertical-align:middle;font-size:11.5px;line-height:1.2;background:rgba(11,149,115,0.08);">91.9</td><td style="padding:5px 2px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15);vertical-align:middle;font-size:11.5px;line-height:1.2;">65.2</td><td style="padding:5px 2px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15);vertical-align:middle;font-size:11.5px;line-height:1.2;"><strong>95.2</strong></td><td style="padding:5px 2px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15);vertical-align:middle;font-size:11.5px;line-height:1.2;">89.5</td><td style="padding:5px 2px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15);vertical-align:middle;font-size:11.5px;line-height:1.2;">89.6</td><td style="padding:5px 2px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15);vertical-align:middle;font-size:11.5px;line-height:1.2;">47.0</td></tr><tr><td data-detail="detail" style="padding:5px 4px 5px 24px;border-bottom:1px solid rgba(128,128,128,0.15);vertical-align:middle"><div style="font-size:11.5px;font-weight:400;line-height:1.2;color:inherit">Parsing</div><div style="margin-top:2px;font-size:10px;opacity:0.65">Accuracy</div></td><td style="padding:5px 2px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15);vertical-align:middle;font-size:11.5px;line-height:1.2;background:rgba(11,149,115,0.08);">96.7</td><td style="padding:5px 2px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15);vertical-align:middle;font-size:11.5px;line-height:1.2;">49.7</td><td style="padding:5px 2px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15);vertical-align:middle;font-size:11.5px;line-height:1.2;"><strong>98.3</strong></td><td style="padding:5px 2px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15);vertical-align:middle;font-size:11.5px;line-height:1.2;">94.1</td><td style="padding:5px 2px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15);vertical-align:middle;font-size:11.5px;line-height:1.2;">89.8</td><td style="padding:5px 2px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15);vertical-align:middle;font-size:11.5px;line-height:1.2;">31.3</td></tr><tr><td colspan="7" style="padding:6px 10px;font-weight:600;font-size:12.5px;border-bottom:1px solid rgba(11,149,115,0.25);background:rgba(11,149,115,0.06)">Translation</td></tr><tr><td style="padding:6px 4px 6px 10px;border-bottom:1px solid rgba(128,128,128,0.15);vertical-align:middle"><div style="font-size:12.5px;font-weight:600;line-height:1.2;color:inherit">FLORES200+</div><div style="margin-top:2px;font-size:10px;opacity:0.65">LLM-as-a-judge</div></td><td style="padding:6px 2px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15);vertical-align:middle;font-size:12.5px;line-height:1.2;background:rgba(11,149,115,0.08);">91.5</td><td style="padding:6px 2px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15);vertical-align:middle;font-size:12.5px;line-height:1.2;">70.6</td><td style="padding:6px 2px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15);vertical-align:middle;font-size:12.5px;line-height:1.2;"><strong>92.8</strong></td><td style="padding:6px 2px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15);vertical-align:middle;font-size:12.5px;line-height:1.2;">84.8</td><td style="padding:6px 2px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15);vertical-align:middle;font-size:12.5px;line-height:1.2;">81.8</td><td style="padding:6px 2px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15);vertical-align:middle;font-size:12.5px;line-height:1.2;">71.2</td></tr><tr><td colspan="7" style="padding:9px 10px 7px;font-weight:700;font-size:11px;letter-spacing:0.05em;text-transform:uppercase;border-bottom:1px solid rgba(11,149,115,0.4);background:rgba(11,149,115,0.22)">Assistant Capabilities</td></tr><tr><td colspan="7" style="padding:6px 10px;font-weight:600;font-size:12.5px;border-bottom:1px solid rgba(11,149,115,0.25);background:rgba(11,149,115,0.06)">Instruction Following</td></tr><tr><td style="padding:6px 4px 6px 10px;border-bottom:1px solid rgba(128,128,128,0.15);vertical-align:middle"><div style="font-size:12.5px;font-weight:600;line-height:1.2;color:inherit">Arabic IFBench^</div><div style="margin-top:2px;font-size:10px;opacity:0.65">Accuracy (prompt-level strict)</div></td><td style="padding:6px 2px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15);vertical-align:middle;font-size:12.5px;line-height:1.2;background:rgba(11,149,115,0.08);"><strong>88.7</strong></td><td style="padding:6px 2px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15);vertical-align:middle;font-size:12.5px;line-height:1.2;">32.2</td><td style="padding:6px 2px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15);vertical-align:middle;font-size:12.5px;line-height:1.2;">80.8</td><td style="padding:6px 2px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15);vertical-align:middle;font-size:12.5px;line-height:1.2;">84.2</td><td style="padding:6px 2px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15);vertical-align:middle;font-size:12.5px;line-height:1.2;">81.3</td><td style="padding:6px 2px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15);vertical-align:middle;font-size:12.5px;line-height:1.2;">40.0</td></tr><tr><td style="padding:6px 4px 6px 10px;border-bottom:1px solid rgba(128,128,128,0.15);vertical-align:middle"><div style="font-size:12.5px;font-weight:600;line-height:1.2;color:inherit">Arabic IFEval</div><div style="margin-top:2px;font-size:10px;opacity:0.65">Accuracy</div></td><td style="padding:6px 2px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15);vertical-align:middle;font-size:12.5px;line-height:1.2;background:rgba(11,149,115,0.08);"><strong>80.0</strong></td><td style="padding:6px 2px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15);vertical-align:middle;font-size:12.5px;line-height:1.2;">66.8</td><td style="padding:6px 2px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15);vertical-align:middle;font-size:12.5px;line-height:1.2;">78.7</td><td style="padding:6px 2px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15);vertical-align:middle;font-size:12.5px;line-height:1.2;">79.5</td><td style="padding:6px 2px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15);vertical-align:middle;font-size:12.5px;line-height:1.2;">77.0</td><td style="padding:6px 2px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15);vertical-align:middle;font-size:12.5px;line-height:1.2;">49.8</td></tr><tr><td colspan="7" style="padding:6px 10px;font-weight:600;font-size:12.5px;border-bottom:1px solid rgba(11,149,115,0.25);background:rgba(11,149,115,0.06)">Long Context</td></tr><tr><td style="padding:6px 4px 6px 10px;border-bottom:1px solid rgba(128,128,128,0.15);vertical-align:middle"><div style="font-size:12.5px;font-weight:600;line-height:1.2;color:inherit">AA-LCR (Ar)</div><div style="margin-top:2px;font-size:10px;opacity:0.65">Accuracy</div></td><td style="padding:6px 2px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15);vertical-align:middle;font-size:12.5px;line-height:1.2;background:rgba(11,149,115,0.08);">75.0</td><td style="padding:6px 2px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15);vertical-align:middle;font-size:12.5px;line-height:1.2;">14.0</td><td style="padding:6px 2px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15);vertical-align:middle;font-size:12.5px;line-height:1.2;">66.0</td><td style="padding:6px 2px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15);vertical-align:middle;font-size:12.5px;line-height:1.2;">-</td><td style="padding:6px 2px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15);vertical-align:middle;font-size:12.5px;line-height:1.2;"><strong>79.0</strong></td><td style="padding:6px 2px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15);vertical-align:middle;font-size:12.5px;line-height:1.2;">-</td></tr><tr><td colspan="7" style="padding:6px 10px;font-weight:600;font-size:12.5px;border-bottom:1px solid rgba(11,149,115,0.25);background:rgba(11,149,115,0.06)">Factuality & Hallucination</td></tr><tr><td style="padding:6px 4px 6px 10px;border-bottom:1px solid rgba(128,128,128,0.15);vertical-align:middle"><div style="font-size:12.5px;font-weight:600;line-height:1.2;color:inherit">HalluScore</div><div style="margin-top:2px;font-size:10px;opacity:0.65">Accuracy</div></td><td style="padding:6px 2px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15);vertical-align:middle;font-size:12.5px;line-height:1.2;background:rgba(11,149,115,0.08);">67.3</td><td style="padding:6px 2px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15);vertical-align:middle;font-size:12.5px;line-height:1.2;">42.4</td><td style="padding:6px 2px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15);vertical-align:middle;font-size:12.5px;line-height:1.2;"><strong>69.7</strong></td><td style="padding:6px 2px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15);vertical-align:middle;font-size:12.5px;line-height:1.2;">69.1</td><td style="padding:6px 2px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15);vertical-align:middle;font-size:12.5px;line-height:1.2;">54.6</td><td style="padding:6px 2px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15);vertical-align:middle;font-size:12.5px;line-height:1.2;">41.7</td></tr><tr><td style="padding:6px 4px 6px 10px;border-bottom:1px solid rgba(128,128,128,0.15);vertical-align:middle"><div style="font-size:12.5px;font-weight:600;line-height:1.2;color:inherit">SimpleQA Verified (Ar)</div><div style="margin-top:2px;font-size:10px;opacity:0.65">Aggregate (2/3 F-score + 1/3 non-hallucination rate)</div></td><td style="padding:6px 2px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15);vertical-align:middle;font-size:12.5px;line-height:1.2;background:rgba(11,149,115,0.08);"><strong>28.1</strong></td><td style="padding:6px 2px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15);vertical-align:middle;font-size:12.5px;line-height:1.2;">7.5</td><td style="padding:6px 2px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15);vertical-align:middle;font-size:12.5px;line-height:1.2;">10.6</td><td style="padding:6px 2px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15);vertical-align:middle;font-size:12.5px;line-height:1.2;">13.3</td><td style="padding:6px 2px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15);vertical-align:middle;font-size:12.5px;line-height:1.2;">8.0</td><td style="padding:6px 2px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15);vertical-align:middle;font-size:12.5px;line-height:1.2;">11.0</td></tr><tr><td data-detail="detail" style="padding:5px 4px 5px 24px;border-bottom:1px solid rgba(128,128,128,0.15);vertical-align:middle"><div style="font-size:11.5px;font-weight:400;line-height:1.2;color:inherit">F-score</div></td><td style="padding:5px 2px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15);vertical-align:middle;font-size:11.5px;line-height:1.2;background:rgba(11,149,115,0.08);">7.1</td><td style="padding:5px 2px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15);vertical-align:middle;font-size:11.5px;line-height:1.2;">6.6</td><td style="padding:5px 2px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15);vertical-align:middle;font-size:11.5px;line-height:1.2;">10.7</td><td style="padding:5px 2px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15);vertical-align:middle;font-size:11.5px;line-height:1.2;"><strong>18.2</strong></td><td style="padding:5px 2px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15);vertical-align:middle;font-size:11.5px;line-height:1.2;">9.2</td><td style="padding:5px 2px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15);vertical-align:middle;font-size:11.5px;line-height:1.2;">10.4</td></tr><tr><td data-detail="detail" style="padding:5px 4px 5px 24px;border-bottom:1px solid rgba(128,128,128,0.15);vertical-align:middle"><div style="font-size:11.5px;font-weight:400;line-height:1.2;color:inherit">Non-hallucination rate</div></td><td style="padding:5px 2px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15);vertical-align:middle;font-size:11.5px;line-height:1.2;background:rgba(11,149,115,0.08);"><strong>70.1</strong></td><td style="padding:5px 2px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15);vertical-align:middle;font-size:11.5px;line-height:1.2;">9.4</td><td style="padding:5px 2px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15);vertical-align:middle;font-size:11.5px;line-height:1.2;">10.5</td><td style="padding:5px 2px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15);vertical-align:middle;font-size:11.5px;line-height:1.2;">3.7</td><td style="padding:5px 2px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15);vertical-align:middle;font-size:11.5px;line-height:1.2;">5.4</td><td style="padding:5px 2px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15);vertical-align:middle;font-size:11.5px;line-height:1.2;">12.2</td></tr><tr><td colspan="7" style="padding:9px 10px 7px;font-weight:700;font-size:11px;letter-spacing:0.05em;text-transform:uppercase;border-bottom:1px solid rgba(11,149,115,0.4);background:rgba(11,149,115,0.22)">Agentic</td></tr><tr><td style="padding:6px 4px 6px 10px;border-bottom:1px solid rgba(128,128,128,0.15);vertical-align:middle"><div style="font-size:12.5px;font-weight:600;line-height:1.2;color:inherit">Terminal Bench 2.1</div><div style="margin-top:2px;font-size:10px;opacity:0.65">Accuracy (Avg@3)</div></td><td style="padding:6px 2px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15);vertical-align:middle;font-size:12.5px;line-height:1.2;background:rgba(11,149,115,0.08);">63.7</td><td style="padding:6px 2px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15);vertical-align:middle;font-size:12.5px;line-height:1.2;">1.1</td><td style="padding:6px 2px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15);vertical-align:middle;font-size:12.5px;line-height:1.2;">43.5</td><td style="padding:6px 2px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15);vertical-align:middle;font-size:12.5px;line-height:1.2;">51.7</td><td style="padding:6px 2px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15);vertical-align:middle;font-size:12.5px;line-height:1.2;"><strong>79.8</strong></td><td style="padding:6px 2px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15);vertical-align:middle;font-size:12.5px;line-height:1.2;">1.1</td></tr><tr><td style="padding:6px 4px 6px 10px;border-bottom:1px solid rgba(128,128,128,0.15);vertical-align:middle"><div style="font-size:12.5px;font-weight:600;line-height:1.2;color:inherit">GDPVal</div><div style="margin-top:2px;font-size:10px;opacity:0.65">Accuracy (@ 75% threshold)</div></td><td style="padding:6px 2px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15);vertical-align:middle;font-size:12.5px;line-height:1.2;background:rgba(11,149,115,0.08);">75.5</td><td style="padding:6px 2px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15);vertical-align:middle;font-size:12.5px;line-height:1.2;">0.0</td><td style="padding:6px 2px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15);vertical-align:middle;font-size:12.5px;line-height:1.2;">30.5</td><td style="padding:6px 2px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15);vertical-align:middle;font-size:12.5px;line-height:1.2;">48.2</td><td style="padding:6px 2px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15);vertical-align:middle;font-size:12.5px;line-height:1.2;"><strong>78.2</strong></td><td style="padding:6px 2px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15);vertical-align:middle;font-size:12.5px;line-height:1.2;">0.0</td></tr><tr><td style="padding:6px 4px 6px 10px;border-bottom:1px solid rgba(128,128,128,0.15);vertical-align:middle"><div style="font-size:12.5px;font-weight:600;line-height:1.2;color:inherit">MCPMark</div><div style="margin-top:2px;font-size:10px;opacity:0.65">Accuracy (Pass@1)</div></td><td style="padding:6px 2px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15);vertical-align:middle;font-size:12.5px;line-height:1.2;background:rgba(11,149,115,0.08);"><strong>66.1</strong></td><td style="padding:6px 2px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15);vertical-align:middle;font-size:12.5px;line-height:1.2;">0.8</td><td style="padding:6px 2px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15);vertical-align:middle;font-size:12.5px;line-height:1.2;">48.8</td><td style="padding:6px 2px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15);vertical-align:middle;font-size:12.5px;line-height:1.2;">44.9</td><td style="padding:6px 2px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15);vertical-align:middle;font-size:12.5px;line-height:1.2;">49.6</td><td style="padding:6px 2px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15);vertical-align:middle;font-size:12.5px;line-height:1.2;">12.1</td></tr><tr><td style="padding:6px 4px 6px 10px;border-bottom:1px solid rgba(128,128,128,0.15);vertical-align:middle"><div style="font-size:12.5px;font-weight:600;line-height:1.2;color:inherit">WildClawBench (English text-only subset)</div><div style="margin-top:2px;font-size:10px;opacity:0.65">Mean Score@3</div></td><td style="padding:6px 2px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15);vertical-align:middle;font-size:12.5px;line-height:1.2;background:rgba(11,149,115,0.08);">42.0</td><td style="padding:6px 2px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15);vertical-align:middle;font-size:12.5px;line-height:1.2;">10.7</td><td style="padding:6px 2px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15);vertical-align:middle;font-size:12.5px;line-height:1.2;">44.1</td><td style="padding:6px 2px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15);vertical-align:middle;font-size:12.5px;line-height:1.2;">43.2</td><td style="padding:6px 2px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15);vertical-align:middle;font-size:12.5px;line-height:1.2;"><strong>52.1</strong></td><td style="padding:6px 2px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15);vertical-align:middle;font-size:12.5px;line-height:1.2;">10.3</td></tr><tr><td style="padding:6px 4px 6px 10px;border-bottom:1px solid rgba(128,128,128,0.15);vertical-align:middle"><div style="font-size:12.5px;font-weight:600;line-height:1.2;color:inherit">Apex-Agents (420 text-only subset, loop agent)</div><div style="margin-top:2px;font-size:10px;opacity:0.65">Pass@1 (Accuracy)</div></td><td style="padding:6px 2px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15);vertical-align:middle;font-size:12.5px;line-height:1.2;background:rgba(11,149,115,0.08);">25.2</td><td style="padding:6px 2px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15);vertical-align:middle;font-size:12.5px;line-height:1.2;">0.7</td><td style="padding:6px 2px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15);vertical-align:middle;font-size:12.5px;line-height:1.2;">12.4</td><td style="padding:6px 2px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15);vertical-align:middle;font-size:12.5px;line-height:1.2;">22.1</td><td style="padding:6px 2px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15);vertical-align:middle;font-size:12.5px;line-height:1.2;"><strong>28.6</strong></td><td style="padding:6px 2px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15);vertical-align:middle;font-size:12.5px;line-height:1.2;">0.2</td></tr><tr><td style="padding:6px 4px 6px 10px;border-bottom:1px solid rgba(128,128,128,0.15);vertical-align:middle"><div style="font-size:12.5px;font-weight:600;line-height:1.2;color:inherit">GAIA v2 lit (Ar)</div><div style="margin-top:2px;font-size:10px;opacity:0.65">Accuracy (Pass@1)</div></td><td style="padding:6px 2px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15);vertical-align:middle;font-size:12.5px;line-height:1.2;background:rgba(11,149,115,0.08);">51.5</td><td style="padding:6px 2px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15);vertical-align:middle;font-size:12.5px;line-height:1.2;">9.7</td><td style="padding:6px 2px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15);vertical-align:middle;font-size:12.5px;line-height:1.2;">42.4</td><td style="padding:6px 2px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15);vertical-align:middle;font-size:12.5px;line-height:1.2;">36.4</td><td style="padding:6px 2px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15);vertical-align:middle;font-size:12.5px;line-height:1.2;"><strong>55.8</strong></td><td style="padding:6px 2px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15);vertical-align:middle;font-size:12.5px;line-height:1.2;">12.1</td></tr><tr><td style="padding:6px 4px 6px 10px;border-bottom:1px solid rgba(128,128,128,0.15);vertical-align:middle"><div style="font-size:12.5px;font-weight:600;line-height:1.2;color:inherit">Arabic File Processing</div><div style="margin-top:2px;font-size:10px;opacity:0.65">Accuracy (@ 75% threshold)</div></td><td style="padding:6px 2px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15);vertical-align:middle;font-size:12.5px;line-height:1.2;background:rgba(11,149,115,0.08);">71.8</td><td style="padding:6px 2px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15);vertical-align:middle;font-size:12.5px;line-height:1.2;">0.0</td><td style="padding:6px 2px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15);vertical-align:middle;font-size:12.5px;line-height:1.2;">4.5</td><td style="padding:6px 2px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15);vertical-align:middle;font-size:12.5px;line-height:1.2;">20.9</td><td style="padding:6px 2px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15);vertical-align:middle;font-size:12.5px;line-height:1.2;"><strong>78.6</strong></td><td style="padding:6px 2px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15);vertical-align:middle;font-size:12.5px;line-height:1.2;">0.0</td></tr><tr><td style="padding:6px 4px 6px 10px;border-bottom:1px solid rgba(128,128,128,0.15);vertical-align:middle"><div style="font-size:12.5px;font-weight:600;line-height:1.2;color:inherit">SWE-Bench Verified (Offline)</div><div style="margin-top:2px;font-size:10px;opacity:0.65">Accuracy (Pass@1)</div></td><td style="padding:6px 2px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15);vertical-align:middle;font-size:12.5px;line-height:1.2;background:rgba(11,149,115,0.08);">72.4</td><td style="padding:6px 2px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15);vertical-align:middle;font-size:12.5px;line-height:1.2;">0.4</td><td style="padding:6px 2px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15);vertical-align:middle;font-size:12.5px;line-height:1.2;">59.0</td><td style="padding:6px 2px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15);vertical-align:middle;font-size:12.5px;line-height:1.2;">71.4</td><td style="padding:6px 2px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15);vertical-align:middle;font-size:12.5px;line-height:1.2;"><strong>73.5</strong></td><td style="padding:6px 2px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15);vertical-align:middle;font-size:12.5px;line-height:1.2;">0.4</td></tr><tr><td style="padding:6px 4px 6px 10px;border-bottom:1px solid rgba(128,128,128,0.15);vertical-align:middle"><div style="font-size:12.5px;font-weight:600;line-height:1.2;color:inherit">BrowseComp-Plus</div><div style="margin-top:2px;font-size:10px;opacity:0.65">Accuracy</div></td><td style="padding:6px 2px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15);vertical-align:middle;font-size:12.5px;line-height:1.2;background:rgba(11,149,115,0.08);"><strong>71.9</strong></td><td style="padding:6px 2px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15);vertical-align:middle;font-size:12.5px;line-height:1.2;">1.8</td><td style="padding:6px 2px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15);vertical-align:middle;font-size:12.5px;line-height:1.2;">42.5</td><td style="padding:6px 2px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15);vertical-align:middle;font-size:12.5px;line-height:1.2;">41.1</td><td style="padding:6px 2px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15);vertical-align:middle;font-size:12.5px;line-height:1.2;">53.0</td><td style="padding:6px 2px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15);vertical-align:middle;font-size:12.5px;line-height:1.2;">3.9</td></tr></tbody></table></div>
<!-- TABLE:END -->
> [!NOTE]
> Starred (\*) benchmarks have been audited for sample quality. Items with ambiguous questions, invalid answer options, or indefensible gold labels were excluded, since they can penalize a correct answer or reward a lucky guess. Scores on these benchmarks are reported on the cleaned sets. The audit methodology, the excluded samples and the verified benchmarks are available in the IFM/Arabic-Benchmark-Auditing collection.
> [!NOTE]
> Benchmarks marked with ^ will be released by IFM soon.
> [!NOTE]
> Scores above are for the BF16 source checkpoint. Quantized variants have not been separately evaluated yet.
Files
| File | Type | Size |
| --- | --- | --- |
| Jais-3-32B-BF16.gguf | BF16 | 69.57 GB |
| Jais-3-32B-Q8_0.gguf | Q8_0 | 36.97 GB |
| Jais-3-32B-Q6_K.gguf | Q6_K | 28.54 GB |
| Jais-3-32B-Q5_K_M.gguf | Q5_K_M | 24.70 GB |
| Jais-3-32B-Q5_0.gguf | Q5_0 | 24.09 GB |
| Jais-3-32B-Q4_K_M.gguf | Q4_K_M | 21.08 GB |
Quickstart
llama.cpp
cmake -B build -DGGML_CUDA=ON
cmake --build build -j --target llama-server
./build/bin/llama-server -hf IFM/Jais-3-32B-GGUF:Q8_0 --jinja -ngl 99 -c 32768 -np 1
Pick a variant with :BF16, :Q8_0, :Q6_K, :Q5_K_M, :Q5_0 or :Q4_K_M, or pass a local file with -m. --jinja enables the embedded chat
template, which handles reasoning_effort and K2 Horizon tool calls; reasoning_content is returned separately from content.
API Usage
> [!TIP]
> Recommended settings: reasoning_effort="high", the sampling hyperparameters in the table below, and at least 32,768 output tokens.
> Reasoning depth is selected per request through chat_template_kwargs. Thinking is returned in reasoning_content and the answer in content.
| Parameter | Default | Thinking mode, English | Thinking mode, Arabic |
|---|---|---|---|
| temperature | 0.2 | 1.0 | 0.7 |
| top_p | 0.95 | 0.95 | 0.95 |
| top_k | 20 | 20 | 20 |
<style>
.tabsA { position: relative; margin: 12px 0 18px; }
.tabsA input { position: absolute; opacity: 0; pointer-events: none; }
.tabsA .barA { display: flex; gap: 2px; border-bottom: 1px solid rgba(128,128,128,0.35); }
.tabsA .barA label { padding: 9px 18px; margin-bottom: -1px; font-size: 13.5px; font-weight: 600; letter-spacing: 0.01em; cursor: pointer; opacity: 0.6; border-bottom: 3px solid transparent; transition: opacity 0.15s, border-color 0.15s; }
.tabsA .barA label:hover { opacity: 1; }
#a1:checked ~ .barA label[for="a1"], #a2:checked ~ .barA label[for="a2"] { opacity: 1; border-bottom-color: #0b9573; }
#a1:focus-visible ~ .barA label[for="a1"], #a2:focus-visible ~ .barA label[for="a2"] { outline: 2px solid #0b9573; outline-offset: -2px; }
.tabsA .pA { display: none; }
#a1:checked ~ .p1, #a2:checked ~ .p2 { display: block; }
.tabsA .pA pre { margin: 0; border: 1px solid rgba(128,128,128,0.25); border-top: none; border-radius: 0 0 8px 8px; }
</style>
<div class="tabsA">
<input type="radio" name="tabsA" id="a1" checked>
<input type="radio" name="tabsA" id="a2">
<div class="barA"><label for="a1">Reasoning Example</label><label for="a2">Tool Calling Example</label></div>
<div class="pA p1">
from openai import OpenAI
client = OpenAI(base_url="http://localhost:8080/v1", api_key="EMPTY")
response = client.chat.completions.create(
model="Jais-3-32B",
messages=[{"role": "user", "content": "لدينا عددان مجموعهما 50 وحاصل ضربهما 600. ما هما العددان؟ اشرح خطوات الحل."}],
temperature=0.7,
top_p=0.95,
max_tokens=32768,
extra_body={"top_k": 20, "chat_template_kwargs": {"reasoning_effort": "high"}},
)
message = response.choices[0].message
print("Reasoning:", getattr(message, "reasoning_content", None))
print("Answer:", message.content)
</div>
<div class="pA p2">
import json
from datetime import datetime
from zoneinfo import ZoneInfo
from openai import OpenAI
client = OpenAI(base_url="http://localhost:8080/v1", api_key="EMPTY")
TIMEZONES = {"أبوظبي": "Asia/Dubai", "الرياض": "Asia/Riyadh", "القاهرة": "Africa/Cairo", "لندن": "Europe/London"}
def get_current_time(city: str) -> dict:
if city not in TIMEZONES:
return {"error": f"مدينة غير معروفة: {city}"}
return {"city": city, "time": datetime.now(ZoneInfo(TIMEZONES[city])).strftime("%H:%M")}
tools = [{
"type": "function",
"function": {
"name": "get_current_time",
"description": "يعيد الوقت الحالي في مدينة معينة",
"parameters": {
"type": "object",
"properties": {"city": {"type": "string", "description": "اسم المدينة بالعربية"}},
"required": ["city"],
},
},
}]
available_tools = {"get_current_time": get_current_time}
messages = [{"role": "user", "content": "كم الساعة الآن في القاهرة؟"}]
for _ in range(5): # call the model, run any requested tools, repeat until it answers
message = client.chat.completions.create(
model="Jais-3-32B",
messages=messages,
tools=tools,
temperature=0.7,
top_p=0.95,
max_tokens=32768,
extra_body={
"top_k": 20,
"chat_template_kwargs": {"reasoning_effort": "high", "tool_call_format": "xml"},
},
).choices[0].message
messages.append(message)
if not message.tool_calls:
break
for call in message.tool_calls:
tool = available_tools.get(call.function.name)
arguments = json.loads(call.function.arguments)
result = tool(**arguments)
messages.append({"role": "tool", "tool_call_id": call.id,
"content": json.dumps(result, ensure_ascii=False)})
print(message.content)
</div>
</div>
Our model supports multiple tool-call formats, which can be changed with chat_template_kwargs. The supported values are json, xml, and xml_typed. The default is xml. Keep --tool-call-parser k2_horizon enabled to parse the selected format.
Best Practices
- Reasoning effort: always
high. All reported results use high reasoning effort. Pass{"chat_template_kwargs": {"reasoning_effort": "high"}}on every request. No reasoning ({"reasoning_effort": "low"}) is not recommended except for research on reasoning efforts. - Sampling parameters. Use the values in the table above:
temperature=0.2,top_p=0.95,top_k=20by default. In thinking mode, settemperature=1.0for English andtemperature=0.7for Arabic. Keepmin_p=0.0,presence_penalty=0.0andrepetition_penalty=1.0. - Parsers. With
--jinja, llama.cpp detects the K2 Horizon template and parses reasoning and tool calls itself; no parser flags are needed.
Intended Use and Limitations
Intended use: The model is designed for Arabic and English assistant and agentic applications, including reasoning and tool-use tasks, as well as for research and experimentation.
Out of scope: The model should not be used in ways that violate applicable laws or regulations. The following uses are also considered out of scope:
- Harmful or malicious use: generating hateful, extremist, discriminatory, or deliberately misleading content, or using the model to support illegal or harmful activities.
- Sensitive information: using the model to generate, expose, or infer personal, confidential, or otherwise sensitive information about individuals or organizations.
- Unsupported languages: applications that depend on reliable performance in languages other than Arabic or English.
- High-stakes decisions: relying on the model to make medical, legal, financial, or safety-critical decisions without appropriate human oversight.
Limitations: The model can produce inaccurate or made-up content and may reflect biases present in its training data. Evaluate it for your use case and add safeguards before deploying it.
Citation
@misc{jais3_2026,
title = {Jais 3: Introducing Arabic-centric Agentic AI},
author = {{IFM Team, Inception42 Team, and Cerebras Team}},
year = {2026},
url = {https://ifm.ai/blog/jais3/},
}Run IFM/Jais-3-32B-GGUF with guIDE
Download guIDE — the AI-native code editor with local LLM inference and 69 built-in tools.
Source: Hugging Face · Compare models