Skip to content

Benchmark

ArxivMath

Math benchmarks measure how well models solve maths problems. Scores are percentages. Higher is better.

Models measured
10
Scores recorded
15
Sources
2
IQ weight
1.57

Score distribution

72.4%
Mean
71.8%
Median
11.7%
Std dev
52.2%
10th percentile
91.2%
90th percentile
52.2%
Min
52.2%91.2%
The band covers the middle 80% of scores. The line marks the median.

This benchmark has a weight of 1.57 for chat models, measured over 10 models. The weight is how much it counts toward llminfo IQ. We measure it from the data, not from the raw scores.

Leaderboard

#ModelScore
1Claude Opus 5.5· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim91.2%
2Claude Opus 5.5Opus 5.5 System Card capability section · August 2026 · no tools · max · 4 attempts/problem· Reported by Anthropic· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.91.2%
3Claude Sonnet 5.5· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim86.8%
4Claude Fable 5.1Opus 5.5 System Card capability section · August 2026 · no tools· Reported by Anthropic· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.82.9%
5Claude Opus 5Opus 5.5 System Card capability section · August 2026 · no tools· Reported by Anthropic· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.78.1%
6Claude Sonnet 5· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim72.2%
7Claude Sonnet 5April + May 2026 · with tools · extended thinking · 4 attempts/problem· Reported by Anthropic· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.72.2%
8Claude Opus 4.8Fable/Mythos 5 System Card capability summary · adaptive thinking · max effort · 5 trials unless noted· Reported by Anthropic· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.71.8%
9GPT 5.5Fable/Mythos 5 System Card capability summary · adaptive thinking · max effort · 5 trials unless noted· Reported by Anthropic· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.71.5%
10Hy4 preview· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim66.6%
11Hy4 previewofficial model-card appendix· Reported by Tencent Hy· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.66.6%
12Claude Sonnet 5April + May 2026 · no tools · extended thinking · 4 attempts/problem· Reported by Anthropic· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.65.7%
13Gemini 3.1 Pro PreviewFable/Mythos 5 System Card capability summary · adaptive thinking · max effort · 5 trials unless noted· Reported by Anthropic· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.64.8%
14Hy3 (Deep Infra)· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim52.2%
15Hy3 (Deep Infra)Hy3 official Benchmark Appendix · highest reasoning tier unless noted· Reported by Tencent Hunyuan· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.52.2%

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