MedCode (Vals AI): current results
Vals AI (dataset with Protege) · 2,755 patient records · index updated August 16, 2026
Claude Opus 5 holds the top current result on MedCode (Vals AI), 63.57% as of 2026-08, per Vals AI MedCode leaderboard. ICD-10-CM diagnosis coding for entire hospital stays: models assign primary and secondary codes from discharge summaries plus progress/consult notes; ground truth double-annotated by certified professional coders.
Current results
- 1
Claude Opus 563.57% - 2
Gemini 3.1 Pro Preview (02/26)59.06% - 3Claude Fable 556.07%
- 4Gemini 3 Flash (12/25)55.92%
- 5Gemini 3.5 Flash55.83%
Result detail
| # | model | score | as of | |
|---|---|---|---|---|
| 1 | | Claude Opus 5 Anthropic | 63.57% | 2026-08 |
| 2 | | Gemini 3.1 Pro Preview (02/26) Google | 59.06% | 2026-08 |
| 3 | | Claude Fable 5 Anthropic | 56.07% | 2026-08 |
| 4 | | Gemini 3 Flash (12/25) Google | 55.92% | 2026-08 |
| 5 | | Gemini 3.5 Flash Google | 55.83% | 2026-08 |
Scores appear exactly as Vals AI MedCode leaderboard publishes them (independently run). Vals AI runs every model itself; 85 models on the board, last updated August 15, 2026. Vals AI pairs this board with MedScribe, and its writeup notes that coding accuracy lags documentation quality.
About the benchmark
| publisher | Vals AI (dataset with Protege) |
|---|---|
| category | documentation and coding benchmarks |
| released | 2026-02 |
| size | 2,755 patient records |
| scale | percentage accuracy 0-100, higher better |
| result basis | independently run |
| source | Vals AI MedCode leaderboard |
| last frontier result | 2026-08 |
What is MedCode (Vals AI)?
MedCode (Vals AI) is a documentation and coding benchmark from Vals AI, released 2026-02: 2,755 patient records, scored on a percentage accuracy 0-100 scale. ICD-10-CM diagnosis coding for entire hospital stays: models assign primary and secondary codes from discharge summaries plus progress/consult notes; ground truth double-annotated by certified professional coders.
Which model leads MedCode (Vals AI)?
Claude Opus 5 (Anthropic) holds the top current result on MedCode (Vals AI) at 63.57%, per Vals AI MedCode leaderboard, as of 2026-08.
Where do the MedCode (Vals AI) numbers come from?
From Vals AI MedCode leaderboard (independently run). Vals AI runs every model itself; 85 models on the board, last updated August 15, 2026. Vals AI pairs this board with MedScribe, and its writeup notes that coding accuracy lags documentation quality.
The rest of the field is on the index, and how sources qualify is on the methodology page. Model names in the table link to cross-benchmark pages.