---

license: mit

language:

• en

pipeline_tag: text-generation

tags:

• reasoning
• math
• code
• qwen2
• mythos-nano

base_model:

• squ11z1/Mythos-nano

base_model_relation: finetune

library_name: transformers

---

> [!NOTE]

> I, (me), just removed the gguf's for those who dont want to download 40GB of model weighs, so now you have the safetensors now for easier use and fine tuning.

<br>

> Disclaimer: This is not an official release by Anthropic.

> Mythos-nano is an independent open model project.

Mythos-nano

!Gemini_Generated_Image_1nl8n11nl8n11nl8

<blockquote style="border-left: 4px solid #ff6b6b; background-color: #fff5f5; padding: 10px 15px; margin: 10px 0; color: #cc3333;">

<span style="font-weight: bold;">🚨 </span> This model was not trained on tool-calling or agent-based programming data. We therefore do not recommend using it for tasks that involve function calling, API orchestration, or autonomous coding agents.

For programming tasks, we recommend using this model on competitive programming problems (e.g., LeetCode-style) - Weibo Lab.

</blockquote>

<blockquote style="border-left: 4px solid #ff6b6b; background-color: #fff5f5; padding: 10px 15px; margin: 10px 0; color: #cc3333;">

<span style="font-weight: bold;">⚠️ </span> Abliterated (uncensored): the refusal direction has been removed, so this model will not decline requests a safety-tuned model normally would. Safety guardrails are reduced — use responsibly and at your own risk; you are solely responsible for outputs and legal compliance.

</blockquote>

🏆 Benchmarks

!ChatGPT Image Jun 19, 2026 at 12_53_05 PM

Full comparison (mathematics · coding · knowledge · instruction)

| Model | Params | AIME25 | AIME26 | HMMT25 | BruMO25 | IMO-Ans | LCBv6 | OJBench | GPQA-D | IFEval | IFBench |

|---|---|---|---|---|---|---|---|---|---|---|---|

| Kimi K2.5 | 1T | 96.1 | 93.3 | 95.4 | 98.3 | 81.8 | 85.0 | 54.7 | 87.6 | 93.9 | 70.0 |

| GLM-5 | 744B | 96.7 | 95.8 | 97.9 | – | 82.5 | 85.5 | 55.0 | 86.0 | 92.6 | 76.5 |

| DeepSeek V3.2 | 671B | 93.1 | 94.2 | 90.2 | 96.7 | 78.3 | 80.8 | 48.4 | 82.4 | 92.6 | 60.7 |

| Gemini 3 Pro | N/A | 96.0 | 91.7 | 97.5 | 98.3 | 83.1 | 87.4 | 58.8 | 91.9 | – | 70.4 |

| Claude Opus 4.5 | N/A | 92.8 | 95.1 | 92.9 | – | 78.5 | 84.8 | – | 87.0 | – | 58.0 |

| GPT-5 (high) | N/A | 94.6 | – | 88.3 | 91.7 | 76.0 | 84.5 | – | 85.7 | – | 73.1 |

| Mythos-nano | 3B | 91.4 | 94.3 | 89.3 | 93.8 | 76.4 | 80.2 | 38.6 | 70.2 | 93.4 | 74.5 |

| Mythos-nano + CLR | 3B | 96.7 | 97.1 | 95.4 | 99.2 | 80.6 | – | – | 72.9 | – | – |

LeetCode contests (Python, pass-rate)

| Model | Aggregate |

|---|---|

| GPT-5.3-Codex | 100.0% (128/128) |

| Gemini 3.1 Pro | 99.2% (127/128) |

| Gemini 3 Flash | 96.9% (124/128) |

| Mythos-nano | 96.1% (123/128) |

| GPT-5.2 | 95.3% (122/128) |

| Qwen3-Max | 91.4% (117/128) |

| Kimi K2.5 | 90.6% (116/128) |

| Claude Opus 4.6 | 86.7% (111/128) |

A 3B model placing within ~4 points of trillion-parameter systems on competition math

and live code — the core thesis: with verifiable feedback, small models reach frontier

reasoning.

Usage

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch
tok = AutoTokenizer.from_pretrained("FlameF0X/Mythos-nano-safetensors-only")
model = AutoModelForCausalLM.from_pretrained("FlameF0X/Mythos-nano-safetensors-only", dtype=torch.bfloat16, device_map="cuda")
msgs = [{"role": "user", "content": "Find all integer solutions of x^2 - y^2 = 12."}]
ids = tok.apply_chat_template(msgs, add_generation_prompt=True, return_tensors="pt").to("cuda")
print(tok.decode(model.generate(ids, max_new_tokens=2048, temperature=0.6)[0], skip_special_tokens=True))

Recommended sampling: temperature 0.6–1.0, up to 40960 output tokens for hard problems.

License

MIT.