Skip to content

Benchmark

Lexam

Scores are percentages. Higher is better.

Models measured
8
Scores recorded
8
Sources
1
IQ weight
1.03

Score distribution

45.6%
Mean
46.6%
Median
3.7%
Std dev
40.8%
10th percentile
48.2%
90th percentile
40.7%
Min
40.7%52.4%
The band covers the middle 80% of scores. The line marks the median.

This benchmark has a weight of 1.03 for chat models, measured over 8 models. The weight is how much it counts toward llminfo IQ. We measure it from the data, not from the raw scores.

Leaderboard

#ModelScore
1DeepSeek R1· Hugging Face Official Benchmarks data· Reported by the model's developer. The source relaying it did not verify it. claim52.4%
2Qwen 3 235B A22B Thinking 2507· Hugging Face Official Benchmarks data· Reported by the model's developer. The source relaying it did not verify it. claim48.2%
3GPT OSS 120B· Hugging Face Official Benchmarks data· Reported by the model's developer. The source relaying it did not verify it. claim47.7%
4DeepSeek V3· Hugging Face Official Benchmarks data· Reported by the model's developer. The source relaying it did not verify it. claim46.6%
5Qwen3 32B· Hugging Face Official Benchmarks data· Reported by the model's developer. The source relaying it did not verify it. claim45.3%
6Qwen3 Next 80B A3Bthinking· Hugging Face Official Benchmarks data· Reported by the model's developer. The source relaying it did not verify it. claim43.3%
7GPT OSS 20b· Hugging Face Official Benchmarks data· Reported by the model's developer. The source relaying it did not verify it. claim40.8%
8Phi 4· Hugging Face Official Benchmarks data· Reported by the model's developer. The source relaying it did not verify it. claim40.7%

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