Skip to content

Benchmark

APEX-1: General Practitioner

Scores are percentages. Higher is better.

Models measured
12
Scores recorded
12
Sources
1
IQ weight
1.18

Score distribution

63.1%
Mean
63.2%
Median
5.3%
Std dev
56.5%
10th percentile
72.1%
90th percentile
56.2%
Min
56.2%73%
The band covers the middle 80% of scores. The line marks the median.

This benchmark has a weight of 1.18 for chat models, measured over 12 models. The weight is how much it counts toward llminfo IQ. We measure it from the data, not from the raw scores.

Leaderboard

#ModelScore
1Claude Opus 5.5clinical-result-2601· Clinical Benchmarks data docs73%
2Claude Opus 5clinical-result-2602· Clinical Benchmarks data docs72.1%
3Gemini 3.8 Flashclinical-result-2603· Clinical Benchmarks data docs68.4%
4Kimi K3clinical-result-2604· Clinical Benchmarks data docs64.4%
5GPT-5.6 Solclinical-result-2605· Clinical Benchmarks data docs63.8%
6GLM 5.3clinical-result-2606· Clinical Benchmarks data docs63.2%
7GPT-6 Astraclinical-result-2607· Clinical Benchmarks data docs61%
8GPT-6.1 Solclinical-result-2608· Clinical Benchmarks data docs60.6%
9Grok 4.6clinical-result-2609· Clinical Benchmarks data docs59.4%
10Grok 4.7clinical-result-2610· Clinical Benchmarks data docs59.2%
11DeepSeek V4 Proclinical-result-2611· Clinical Benchmarks data docs56.5%
12DeepSeek V4.1 Flashclinical-result-2612· Clinical Benchmarks data docs56.2%

Data credits: Clinical Benchmarks (clinicalbenchmarks.ai), CC BY 4.0; fractions converted to percentages; source documents retain their own terms (licence)