Skip to content

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
6.7%100%
The band covers the middle 80% of scores. The line marks the median.

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

#ModelScore
101Claude Opus 4.1· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim78%
102MiniMax M2· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it.78%
103Phi 4 Reasoning Plus· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim78%
104MiniMax M1 80K· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it.76.9%
105Claude Opus 4· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim75.5%
106Claude 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%
107Qwen3 VL 235B· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it.74.7%
108MiniMax M1 40K· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it.74.6%
109GPT 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%
110Qwen3 32B· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim72.9%
111Llama 3.1 Nemotron Ultra 253B v1· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim72.5%
112GPT 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%
113Ministral 3Blatest· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim72.1%
114Nemotron Nano 9b V2· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim72.1%
115Gemini 2.5 Flash· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim72%
116Qwen3 30B A3B· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim70.9%
117Claude Sonnet 4· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim70.5%
118Claude 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%
119Qwen3 14B· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim70.4%
120Qwen3 235B A22B Instruct 2507· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim70.3%
121Qwen3 Next 80B A3B Instruct· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim69.5%
122qwen3-vl-30b· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it.69.3%
123Qwen3 VL 32B Instruct· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it.66.2%
124Magistral Medium· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim64.9%
125longcat-flash-lite· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim63.2%
126Phi-4-reasoning· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim62.9%
127Magistral Small 25092506· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim62.8%
128LongCat Flash Chat· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim61.3%
129Llama 3.3 Nemotron Super 49B v1· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim58.4%
130GPT 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%
131Claude Sonnet 3.7· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim54.8%
132LFM2.5 2.6B· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim51.9%
133GPT 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%
134DeepSeek V3.1· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim49.8%
135Gemini 2.5 Flash-Lite· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim49.8%
136Kimi K2 Instruct· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim49.5%
137GPT 4.1· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim46.4%
138Qwen3 VL 8B Instruct· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it.45.9%
139GPT-5.1 Codex Mini· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim42.1%
140GPT-4.1 mini· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim40.2%
141GPT 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%
142Claude 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%
143Claude 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%
144Trinity 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%
145Trinity 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%
146Gemma 3n E4B IT· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim11.6%
147Gemma 3n E2b It· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim6.7%

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