Skip to content

Benchmark

MedXpertQA

Scores are percentages.

Models measured
10
Scores recorded
10
Sources
1
IQ weight
1.65

Score distribution

53.3%
Mean
61.3%
Median
16.4%
Std dev
28.7%
10th percentile
67.3%
90th percentile
23.5%
Min
23.5%78.4%
The band covers the middle 80% of scores. The line marks the median.

This benchmark has a weight of 1.65 for chat models, measured over 10 models. The weight is how much it counts toward llminfo IQ. We measure it from the data, not from the raw scores.

Leaderboard

#ModelScore
1Muse Spark· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim78.4%
2Qwen3.5 122B-A10B· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim67.3%
3Qwen3.5 27B· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim62.4%
4Qwen3.5 35B A3B· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim61.4%
5Gemma 4 31B IT· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim61.3%
6Gemma 4 26B A4B· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim58.1%
7Gemma 4 12B It· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim48.7%
8Mai Thinking 1· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim43%
9Gemma 4 E4B-it· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim28.7%
10Gemma 4 E2B-it· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim23.5%

Data credits: Data by LLM Stats