MedCode
As of Nov 3, 2026, MedCode (v1) is maintained by Vals AI. Metric accuracy (%). Ceiling 100. Saturation unknown. Contamination risk low.
- Maintainer
- Vals AI
- Metric
- accuracy (%)
- Ceiling
- 100
- Saturation
- unknown
- Contamination
- low
- Cadence
- Declared cadence: as Vals updates (checked daily). Catalog snapshots: 1, latest Oct 30, 2026.
- Source
- Vals AI · this benchmark on Vals AI
- Grading
- Automatic (tests or exact checks) — Diagnosis codes for full hospital stays are compared with certified coders' annotations. Dataset built with Protege.
Source: Vals AI. A proprietary private test set run by Vals; scores are republished with permission. Rows are dated the day isitsota first saw them, and only the benchmark's standard harness counts.
Categories
Where it counts
- Healthcare — primary, weight 1
Top 5
Current top scores
- Claude Opus 5 · 63.57 · Oct 30, 2026
- Gemini 3.1 Pro Preview · 59.062 · Oct 30, 2026
- Gemini 4 Argon · 58.801 · Oct 30, 2026
- Claude Fable 5 · 56.07 · Oct 30, 2026
- Gemini 3 Flash Preview · 55.92 · Oct 30, 2026
| Model | Score | Date | Kind |
|---|---|---|---|
| Claude Opus 5 | 63.57 | 2026-10-30 | snapshot |
| Gemini 3.1 Pro Preview | 59.062 | 2026-10-30 | snapshot |
| Gemini 4 Argon | 58.801 | 2026-10-30 | snapshot |
| Claude Fable 5 | 56.07 | 2026-10-30 | snapshot |
| Gemini 3 Flash Preview | 55.92 | 2026-10-30 | snapshot |
| Gemini 3.5 Flash | 55.825 | 2026-10-30 | snapshot |
| Claude Opus 4.7 | 54.858 | 2026-10-30 | snapshot |
| Claude Fable 5.1 | 53.509 | 2026-10-30 | snapshot |
| Gemini 3.7 Flash | 53.39 | 2026-10-30 | snapshot |
| Claude Opus 4.8 | 53.217 | 2026-10-30 | snapshot |
| Gemini 3.6 Flash | 53.153 | 2026-10-30 | snapshot |
| Claude Sonnet 5.5 | 52.92 | 2026-10-30 | snapshot |
| GPT-5.1 | 52.732 | 2026-10-30 | snapshot |
| Gemini 3 Pro Preview | 52.198 | 2026-10-30 | snapshot |
| Claude Haiku 5.5 | 51.542 | 2026-10-30 | snapshot |
| Muse Spark | 51.31 | 2026-10-30 | snapshot |
| Gemini 2.5 Pro | 50.59 | 2026-10-30 | snapshot |
| Muse Wonder Full | 49.932 | 2026-10-30 | snapshot |
| Claude Opus 5.5 | 49.797 | 2026-10-30 | snapshot |
| GPT-5.2 | 49.749 | 2026-10-30 | snapshot |
| GPT-5 | 49.634 | 2026-10-30 | snapshot |
| Grok 4.7 | 49.553 | 2026-10-30 | snapshot |
| Kimi K3 | 49.357 | 2026-10-30 | snapshot |
| Muse Spark 1.2 | 49.346 | 2026-10-30 | snapshot |
| Claude Opus 4.5 20251101 Thinking | 49.156 | 2026-10-30 | snapshot |
| Claude Opus 4.6 Thinking | 49.129 | 2026-10-30 | snapshot |
| GPT-5.5 | 49.1 | 2026-10-30 | snapshot |
| GPT-6.1 Sol | 48.839 | 2026-10-30 | snapshot |
| GPT-6 Astra | 48.486 | 2026-10-30 | snapshot |
| Claude Opus 4.6 | 48.244 | 2026-10-30 | snapshot |