Skip to content

Benchmark

LiveBench 20241125

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

Models measured
11
Scores recorded
13
Sources
1
IQ weight
1.82

Score distribution

72.9%
Mean
74.7%
Median
4.8%
Std dev
65.4%
10th percentile
78.4%
90th percentile
62%
Min
62%79.6%
The band covers the middle 80% of scores. The line marks the median.

This benchmark has a weight of 1.82 for chat models, measured over 11 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 VL 235Bthinking· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it.79.6%
2Qwen 3 235B A22B Thinking 2507· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim78.4%
3Qwen3 Next 80B A3Bthinking· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim76.6%
4Qwen3 Next 80B A3B Instruct· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim75.8%
5Qwen3 235B A22B Instruct 2507· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim75.4%
6Qwen3 VL 235B· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it.74.8%
7Qwen3 VL 32B Thinking· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it.74.7%
8Qwen3 VL 32B Instruct· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it.72.2%
9qwen3-vl-30bthinking· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it.72.1%
10Qwen3 14B· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim71.3%
11Qwen: Qwen3 VL 8B Thinking· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it.69.8%
12qwen3-vl-30b· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it.65.4%
13Qwen3 VL 8B Instruct· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it.62%

Data credits: Data by LLM Stats