Skip to content

Benchmark

MATH (CoT)

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

Models measured
3
Scores recorded
3
Sources
1
IQ weight
No weight published

Score distribution

62.5%
Mean
67.6%
Median
7.5%
Std dev
51.9%
10th percentile
68%
90th percentile
51.9%
Min
51.9%68%
The band covers the middle 80% of scores. The line marks the median.

Leaderboard

#ModelScore
1Llama 3.1 70B Instruct· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim68%
2Mistral Large 3· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim67.6%
3Llama 3.1 8B Instruct· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim51.9%

Data credits: Data by LLM Stats