Skip to content

Benchmark

Vals MedCode

Scores are percentages. Higher is better.

Models measured
99
Scores recorded
197
Sources
2
IQ weight
1.68

Score distribution

42%
Mean
42.4%
Median
9%
Std dev
31.3%
10th percentile
53.2%
90th percentile
19.7%
Min
19.7%63.6%
The band covers the middle 80% of scores. The line marks the median.

This benchmark has a weight of 1.68 for chat models, measured over 99 models. The weight is how much it counts toward llminfo IQ. We measure it from the data, not from the raw scores.

Leaderboard

#ModelScore
151MiniMax M2.1· Vals AI34.1%
152MiniMax M2.1clinical-result-2032· Clinical Benchmarks data docs34.1%
153Claude Sonnet 4· Vals AI33.9%
154Claude Sonnet 4clinical-result-2033· Clinical Benchmarks data docs33.9%
155o4 Mini· Vals AI33.8%
156o4 Miniclinical-result-2034· Clinical Benchmarks data docs33.8%
157Mistral Medium 3.5· Vals AI33.8%
158Mistral Medium 3.5clinical-result-2035· Clinical Benchmarks data docs33.8%
159Qwen3.5 Flashclinical-result-2036· Clinical Benchmarks data docs33%
160Qwen3.5 Flash· Vals AI33%
161GLM 4.7· Vals AI32.8%
162GLM 4.7clinical-result-2037· Clinical Benchmarks data docs32.8%
163Claude Haiku 4.5clinical-result-2038· Clinical Benchmarks data docs32.7%
164Claude Haiku 4.5thinking· Vals AI32.7%
165MiMo V2.5 Pro· Vals AI32.5%
166MiMo V2.5 Proclinical-result-2039· Clinical Benchmarks data docs32.5%
167Ling 3.0 Flashclinical-result-2040· Clinical Benchmarks data docs32.3%
168Grok 4.20clinical-result-2041· Clinical Benchmarks data docs32.2%
169Grok 4.20· Vals AI32.2%
170MiMo V2.5· Vals AI31.9%
171MiMo V2.5clinical-result-2042· Clinical Benchmarks data docs31.9%
172Qwen3 VL Plus· Vals AI31.7%
173Qwen3 VL Plusclinical-result-2043· Clinical Benchmarks data docs31.7%
174Qwen3 Max· Vals AI31.4%
175Qwen3 Maxclinical-result-2044· Clinical Benchmarks data docs31.4%
176Mercury 2.5clinical-result-2045· Clinical Benchmarks data docs31.3%
177Mercury 2.5· Vals AI31.3%
178GPT-5 nano· Vals AI30.4%
179GPT-5 nanoclinical-result-2046· Clinical Benchmarks data docs30.4%
180Grok 4 Fastclinical-result-2047, non-reasoning· Clinical Benchmarks data docs30%
181Ling 3.0 Flash Finclinical-result-2048· Clinical Benchmarks data docs29.3%
182Qwen 3.8 27Bclinical-result-2049· Clinical Benchmarks data docs28.7%
183Qwen 3.8 27B· Vals AI28.7%
184Grok 4.1 Fastclinical-result-2050, non-reasoning· Clinical Benchmarks data docs28.4%
185Grok 4.1 Fast· Vals AI28.3%
186Grok 4.1 Fastclinical-result-2051, reasoning· Clinical Benchmarks data docs28.1%
187Gemini 2.5 Flash-Lite· Vals AI27.1%
188Gemini 2.5 Flash-Liteclinical-result-2052· Clinical Benchmarks data docs27.1%
189Gemini 2.5 Flash Lite Preview 09-2025· Vals AI27.1%
190Llama 4 Scout· Vals AI23.3%
191Llama 4 Scoutclinical-result-2054· Clinical Benchmarks data docs23.3%
192Laguna M.1clinical-result-2055· Clinical Benchmarks data docs23.1%
193Laguna M.1· Vals AI23.1%
194Laguna XS.2· Vals AI21.3%
195Laguna XS.2clinical-result-2056· Clinical Benchmarks data docs21.3%
196Command A Plusclinical-result-2057· Clinical Benchmarks data docs19.7%
197Command A Plus 05 2026· Vals AI19.7%

Showing 151–197 of 197 results.

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