Benchmark
MedXpertQA (MM)
Scores are percentages. Higher is better.
- Models measured
- 23
- Scores recorded
- 31
- Sources
- 3
- IQ weight
- 2.15
Score distribution
- 65%
- Mean
- 68.7%
- Median
- 14%
- Std dev
- 47.6%
- 10th percentile
- 80.4%
- 90th percentile
- 23.5%
- Min
This benchmark has a weight of 2.15 for chat models, measured over 23 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 | GPT-5.6 Solclinical-result-548· Clinical Benchmarks data docs | 81.5% |
| 2 | Gemini 3.1 Pro Previewclinical-result-156· Clinical Benchmarks data docs | 81.3% |
| 3 | Qwen3.8 Maxclinical-result-157· Clinical Benchmarks data docs· Reported by the model's developer. The source relaying it did not verify it. claim | 80.4% |
| 4 | Qwen3.8 MaxQwen3.8-Max release vision/video table · published setting· Reported by Qwen· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 80.4% |
| 5 | Claude Fable 5clinical-result-547· Clinical Benchmarks data docs | 80% |
| 6 | Muse Sparkclinical-result-158· Clinical Benchmarks data docs· Reported by the model's developer. The source relaying it did not verify it. claim | 78.4% |
| 7 | GPT 5.4clinical-result-159· Clinical Benchmarks data docs | 77.1% |
| 8 | Gemini 3 Pro Previewclinical-result-1823· Clinical Benchmarks data docs | 76% |
| 9 | GPT 5.2clinical-result-550· Clinical Benchmarks data docs | 73.3% |
| 10 | Claude Opus 4.8clinical-result-546· Clinical Benchmarks data docs | 71.7% |
| 11 | Qwen3.7 Plus· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 71% |
| 12 | Qwen3.7 Plusclinical-result-160· Clinical Benchmarks data docs· Reported by the model's developer. The source relaying it did not verify it. claim | 71% |
| 13 | Qwen3.7 PlusQwen3.7-Plus release · published setting· Reported by Qwen· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 71% |
| 14 | Qwen3.5 397B A17Bclinical-result-552· Clinical Benchmarks data docs· Reported by the model's developer. The source relaying it did not verify it. claim | 70% |
| 15 | Qwen3.5 397B A17BQwen3.5 release/model card · published setting· Reported by Qwen· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 70% |
| 16 | Qwen3.6 Plusclinical-result-549· Clinical Benchmarks data docs· Reported by the model's developer. The source relaying it did not verify it. claim | 68.7% |
| 17 | Grok 4.20clinical-result-161· Clinical Benchmarks data docs | 65.8% |
| 18 | Kimi K2.5clinical-result-551· Clinical Benchmarks data docs | 65.3% |
| 19 | Claude Opus 4.6clinical-result-162· Clinical Benchmarks data docs | 64.8% |
| 20 | Claude Opus 4.5clinical-result-1824· Clinical Benchmarks data docs | 63.6% |
| 21 | Gemma 4 31B ITclinical-result-1825· Clinical Benchmarks data docs· Reported by the model's developer. The source relaying it did not verify it. claim | 61.3% |
| 22 | Gemma 4 31B ITGemma 4 Technical Report · Table 6 · thinking · 1120 vision tokens· Reported by Google DeepMind· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 61.3% |
| 23 | Gemma 4 31B ITGemma 4 Technical Report · Table 12 · thinking · 280 vision tokens· Reported by Google DeepMind· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 60.7% |
| 24 | Gemma 4 26B A4Bclinical-result-1826· Clinical Benchmarks data docs· Reported by the model's developer. The source relaying it did not verify it. claim | 58.1% |
| 25 | Gemma 4 26B A4BGemma 4 Technical Report · Table 6 · thinking · 1120 vision tokens· Reported by Google DeepMind· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 58.1% |
| 26 | Gemma 4 26B A4BGemma 4 Technical Report · Table 12 · thinking · 280 vision tokens· Reported by Google DeepMind· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 55.7% |
| 27 | Qwen3.5 Omni PlusQwen3.5-Omni release · published setting· Reported by Qwen, Qwen Team· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 54.7% |
| 28 | Qwen3 VL 235Bclinical-result-1827· Clinical Benchmarks data docs· Reported by the model's developer. The source relaying it did not verify it. claim | 47.6% |
| 29 | Qwen3.5 Omni FlashQwen3.5-Omni release · published setting· Reported by Qwen, Qwen Team· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 44.8% |
| 30 | gemma 4 E4Bclinical-result-1828· Clinical Benchmarks data docs· Reported by the model's developer. The source relaying it did not verify it. claim | 28.7% |
| 31 | Gemma 4 E2B ITclinical-result-1829· Clinical Benchmarks data docs· Reported by the model's developer. The source relaying it did not verify it. claim | 23.5% |
Data credits: Clinical Benchmarks (clinicalbenchmarks.ai), CC BY 4.0; fractions converted to percentages; source documents retain their own terms (licence) · BenchBoard by SYuan03 (github.com/SYuan03/benchboard). MIT covers its code and data organization; no results licence is inferred. Numeric relays retain the original stating-source links. · Data by LLM Stats