Skip to content

Benchmark

HMMT February 2026

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

Models measured
5
Scores recorded
5
Sources
1
IQ weight
0.41

Score distribution

86.4%
Mean
86.4%
Median
1.3%
Std dev
84.1%
10th percentile
87.9%
90th percentile
84.1%
Min
84.1%87.9%
The band covers the middle 80% of scores. The line marks the median.

This benchmark has a weight of 0.41 for chat models, measured over 5 models. The weight is how much it counts toward llminfo IQ. We measure it from the data, not from the raw scores.

Leaderboard

#ModelScore
1Qwen3.5 397B A17B· OpenEvals Leaderboard data· Reported by the model's developer. The source relaying it did not verify it.87.9%
2Kimi K2.5· OpenEvals Leaderboard data· Reported by the model's developer. The source relaying it did not verify it.87.1%
3GLM 5· OpenEvals Leaderboard data· Reported by the model's developer. The source relaying it did not verify it.86.4%
4Step 3.5 Flash· OpenEvals Leaderboard data· Reported by the model's developer. The source relaying it did not verify it.86.4%
5DeepSeek V3.2· OpenEvals Leaderboard data· Reported by the model's developer. The source relaying it did not verify it.84.1%

Data credits: OpenEvals/leaderboard-data, MIT (licence)