Skip to content

Benchmark

AlignBench

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

Models measured
5
Scores recorded
5
Sources
1
IQ weight
0.67

Score distribution

78.6%
Mean
80.4%
Median
5.1%
Std dev
72.1%
10th percentile
85.6%
90th percentile
72.1%
Min
72.1%85.6%
The band covers the middle 80% of scores. The line marks the median.

This benchmark has a weight of 0.67 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 14B· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim85.6%
2Qwen2.5 72B Instruct· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim81.6%
3DeepSeek V2.5· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim80.4%
4Qwen2.5 7B Instruct· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim73.3%
5Qwen2 7B Instruct· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim72.1%

Data credits: Data by LLM Stats