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
51Claude Opus 4.5no tools · 64K thinking · 200K context · avg@5 · contamination caveat· Reported by Anthropic· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.92.8%
52o4 Mini· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim92.7%
53GPT OSS 120Bhigh· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim92.5%
54GPT OSS 120Bofficial model card Table 3 · reasoning high · no tools · pass@1· Reported by OpenAI· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.92.5%
55Qwen 3 235B A22B Thinking 2507· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim92.3%
56Grok 4 Fast· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim92%
57GPT OSS 20bofficial model card Table 3 · reasoning high · no tools · pass@1· Reported by OpenAI· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.91.7%
58Grok 4· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim91.7%
59GLM 4.7 Flash· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim91.6%
60GPT OSS 120Bofficial model card Table 3 · reasoning medium · 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.91.6%
61GPT-5 mini· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim91.1%
62Mercury 2· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim91.1%
63Nova 2 Lite· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim91%
64Nova 2 LiteAmazon Nova 2 Lite official launch chart / technical report · accuracy, v1· Reported by Amazon Web Services, Amazon AGI· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.91%
65Grok 3 Mini· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim90.8%
66GPT OSS 20bofficial model card Table 3 · reasoning medium · 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.90.4%
67Nemotron 3 Super 120B A12B· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim90.2%
68Nemotron 3 Super 120B A12BNeMo Evaluator / mostly NeMo Skills · no tools· Reported by NVIDIA· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.90.2%
69Claude Opus 4extended thinking · parallel test-time compute · top_p 0.95· Reported by Anthropic· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.90%
70Command A Plus 05 2026· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim90%
71Qwen3 VL 235Bthinking· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it.89.7%
72DeepSeek V3.2 Exp· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim89.3%
73Granite 4.2 30B· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim89.2%
74Gemini 2.5 Pro· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim88%
75Qwen3 Next 80B A3Bthinking· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim87.8%
76DeepSeek R1· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim87.5%
77Claude Sonnet 4.5· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim87%
78Claude Sonnet 4.5no tools· Reported by Anthropic· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.87%
79ERNIE 5.0· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim87%
80Seed 2.0 Mini· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim87%
81Granite 4.2 8B· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim86.7%
82OpenAI o3· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim86.4%
83MiniMax M2.5official appendix· Reported by MiniMax· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.86.3%
84Mistral Medium 3.5· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim86.3%
85GPT-5 nano· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim85.2%
86Claude Sonnet 4extended thinking · parallel test-time compute · top_p 0.95· Reported by Anthropic· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.85%
87Ministral 14Blatest· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim85%
88Mistral Smalllatest· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim83.8%
89Qwen3 VL 32B Thinking· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it.83.7%
90qwen3-vl-30bthinking· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it.83.1%
91Qwen3 Max· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim81.6%
92Qwen 3 235B A22B· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim81.5%
93GPT-5.5 Instant· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim81.2%
94MiniMax M2.1· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim81%
95Claude Haiku 4.5· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim80.7%
96Claude Haiku 4.5no tools· Reported by Anthropic· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.80.7%
97Qwen: Qwen3 VL 8B Thinking· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it.80.3%
98GPT OSS 120Bofficial 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.80%
99Ministral 8Blatest· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim78.7%
100Granite 4.2 3B· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim78.3%

Showing 51–100 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