Skip to content

Benchmark

Extractbench

Scores are percentages. Higher is better.

Models measured
7
Scores recorded
7
Sources
1
IQ weight
1.28

Score distribution

80.6%
Mean
87.1%
Median
14.8%
Std dev
80.8%
10th percentile
89.8%
90th percentile
45.2%
Min
45.2%89.9%
The band covers the middle 80% of scores. The line marks the median.

This benchmark has a weight of 1.28 for chat models, measured over 7 models. The weight is how much it counts toward llminfo IQ. We measure it from the data, not from the raw scores.

Leaderboard

#ModelScore
1Qwen 3.8 Flash Next· Hugging Face Official Benchmarks data· Reported by the model's developer. The source relaying it did not verify it. claim89.9%
2Qwen 3.8 27B· Hugging Face Official Benchmarks data· Reported by the model's developer. The source relaying it did not verify it. claim89.8%
3Qwen3.6 35B A3B· Hugging Face Official Benchmarks data· Reported by the model's developer. The source relaying it did not verify it. claim88.1%
4DeepSeek V4.1 Flash· Hugging Face Official Benchmarks data· Reported by the model's developer. The source relaying it did not verify it. claim87.1%
5Kimi K3· Hugging Face Official Benchmarks data· Reported by the model's developer. The source relaying it did not verify it. claim83.2%
6GLM 5.3 Flash· Hugging Face Official Benchmarks data· Reported by the model's developer. The source relaying it did not verify it. claim80.8%
7GLM 4.6V Flash· Hugging Face Official Benchmarks data· Reported by the model's developer. The source relaying it did not verify it. claim45.2%

Data credits: Hugging Face official benchmark leaderboards; licence varies by benchmark