Benchmark
APEX-1: General Practitioner
Scores are percentages. Higher is better.
Benchmark sourceScores from Clinical Benchmarks data docs.
- 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
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
| # | Model | Score |
|---|---|---|
| 1 | Claude Opus 5.5clinical-result-2601· Clinical Benchmarks data docs | 73% |
| 2 | Claude Opus 5clinical-result-2602· Clinical Benchmarks data docs | 72.1% |
| 3 | Gemini 3.8 Flashclinical-result-2603· Clinical Benchmarks data docs | 68.4% |
| 4 | Kimi K3clinical-result-2604· Clinical Benchmarks data docs | 64.4% |
| 5 | GPT-5.6 Solclinical-result-2605· Clinical Benchmarks data docs | 63.8% |
| 6 | GLM 5.3clinical-result-2606· Clinical Benchmarks data docs | 63.2% |
| 7 | GPT-6 Astraclinical-result-2607· Clinical Benchmarks data docs | 61% |
| 8 | GPT-6.1 Solclinical-result-2608· Clinical Benchmarks data docs | 60.6% |
| 9 | Grok 4.6clinical-result-2609· Clinical Benchmarks data docs | 59.4% |
| 10 | Grok 4.7clinical-result-2610· Clinical Benchmarks data docs | 59.2% |
| 11 | DeepSeek V4 Proclinical-result-2611· Clinical Benchmarks data docs | 56.5% |
| 12 | DeepSeek V4.1 Flashclinical-result-2612· Clinical Benchmarks data docs | 56.2% |
Data credits: Clinical Benchmarks (clinicalbenchmarks.ai), CC BY 4.0; fractions converted to percentages; source documents retain their own terms (licence)