Medicine
MedHELM HEAD-QA
MedHELM head_qa: per-(model, item) exact_match in {0,1} (1=correct) on 1000 Spanish healthcare specialization (MIR/medicine/pharmacy/nursing) exam questions. 13 models from the MedHELM v4.0.0 release.
1,000items
13subjects
100%observed
Apache-2.0license
medicinedomain
multilingualdomain
textmodality
Response matrix
Fit to width. Hover for subject & item; click a cell for details.
Correct (1)Incorrect (0)Unobserved
Scale: 1 = correct · 0 = incorrect
Subjects
- 1openai/gpt-5-2025-08-070.937
- 2google/gemini-2.5-pro-preview-05-060.931
- 3openai/gpt-5-mini-2025-08-070.928
- 4openai/o4-mini-2025-04-160.923
- 5anthropic/claude-3-7-sonnet-202502190.912
- 6anthropic/claude-3-5-sonnet-202410220.906
- 7openai/gpt-4o-2024-05-130.906
- 8openai/o3-mini-2025-01-310.893
- 9google/gemini-2.0-flash-0010.88
- 10meta/llama-3.3-70b-instruct0.854
- 11google/gemini-1.5-pro-0010.84
- 12openai/gpt-4o-mini-2024-07-180.832
- 13deepseek-ai/deepseek-r10.721