Benchmark
AIME 2025
Math benchmarks measure how well models solve maths problems. Scores are percentages. Higher is better.
- Models measured
- 104
- Scores recorded
- 147
- Sources
- 2
- IQ weight
- 1.67
Score distribution
- 81.5%
- Mean
- 88%
- Median
- 19.2%
- Std dev
- 51.9%
- 10th percentile
- 99.6%
- 90th percentile
- 6.7%
- Min
This benchmark has a weight of 1.67 for chat models, measured over 104 models. The weight is how much it counts toward llminfo IQ. We measure it from the data, not from the raw scores.
Leaderboard
| # | Model | Score |
|---|---|---|
| 101 | Claude Opus 4.1· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 78% |
| 102 | MiniMax M2· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. | 78% |
| 103 | Phi 4 Reasoning Plus· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 78% |
| 104 | MiniMax M1 80K· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. | 76.9% |
| 105 | Claude Opus 4· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 75.5% |
| 106 | Claude Opus 4extended thinking up to 64K tokens · top_p 0.95· Reported by Anthropic· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 75.5% |
| 107 | Qwen3 VL 235B· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. | 74.7% |
| 108 | MiniMax M1 40K· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. | 74.6% |
| 109 | GPT OSS 120Bofficial model card Table 3 · reasoning low · with tools; Table 3 does not name the exact tool · pass@1· Reported by OpenAI· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 72.9% |
| 110 | Qwen3 32B· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 72.9% |
| 111 | Llama 3.1 Nemotron Ultra 253B v1· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 72.5% |
| 112 | GPT OSS 20bofficial model card Table 3 · reasoning medium · no tools · pass@1· Reported by OpenAI· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 72.1% |
| 113 | Ministral 3Blatest· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 72.1% |
| 114 | Nemotron Nano 9b V2· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 72.1% |
| 115 | Gemini 2.5 Flash· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 72% |
| 116 | Qwen3 30B A3B· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 70.9% |
| 117 | Claude Sonnet 4· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 70.5% |
| 118 | Claude Sonnet 4extended thinking up to 64K tokens · top_p 0.95· Reported by Anthropic· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 70.5% |
| 119 | Qwen3 14B· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 70.4% |
| 120 | Qwen3 235B A22B Instruct 2507· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 70.3% |
| 121 | Qwen3 Next 80B A3B Instruct· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 69.5% |
| 122 | qwen3-vl-30b· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. | 69.3% |
| 123 | Qwen3 VL 32B Instruct· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. | 66.2% |
| 124 | Magistral Medium· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 64.9% |
| 125 | longcat-flash-lite· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 63.2% |
| 126 | Phi-4-reasoning· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 62.9% |
| 127 | Magistral Small 25092506· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 62.8% |
| 128 | LongCat Flash Chat· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 61.3% |
| 129 | Llama 3.3 Nemotron Super 49B v1· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 58.4% |
| 130 | GPT OSS 20bofficial model card Table 3 · reasoning low · with tools; Table 3 does not name the exact tool · pass@1· Reported by OpenAI· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 57.5% |
| 131 | Claude Sonnet 3.7· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 54.8% |
| 132 | LFM2.5 2.6B· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 51.9% |
| 133 | GPT OSS 120Bofficial model card Table 3 · reasoning low · no tools · pass@1· Reported by OpenAI· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 50.4% |
| 134 | DeepSeek V3.1· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 49.8% |
| 135 | Gemini 2.5 Flash-Lite· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 49.8% |
| 136 | Kimi K2 Instruct· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 49.5% |
| 137 | GPT 4.1· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 46.4% |
| 138 | Qwen3 VL 8B Instruct· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. | 45.9% |
| 139 | GPT-5.1 Codex Mini· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 42.1% |
| 140 | GPT-4.1 mini· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 40.2% |
| 141 | GPT OSS 20bofficial model card Table 3 · reasoning low · no tools · pass@1· Reported by OpenAI· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 37.1% |
| 142 | Claude Opus 4no extended thinking · top_p 0.95· Reported by Anthropic· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 33.9% |
| 143 | Claude Sonnet 4no extended thinking · top_p 0.95· Reported by Anthropic· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 33.1% |
| 144 | Trinity Large PreviewTrinity technical report · Table 4 · exact reported precision· Reported by Arcee AI· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 24.4% |
| 145 | Trinity Large PreviewTrinity-Large-Preview Model Card · rounded to one decimal· Reported by Arcee AI· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 24% |
| 146 | Gemma 3n E4B IT· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 11.6% |
| 147 | Gemma 3n E2b It· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 6.7% |
Showing 101–147 of 147 results.
Data credits: BenchBoard by SYuan03 (github.com/SYuan03/benchboard). MIT covers its code and data organization; no results licence is inferred. Numeric relays retain the original stating-source links. · Data by LLM Stats