Benchmarks · knowledge
MedScribe
Can models support doctors with their administrative work?
62 models · 62 results · updated 2026-10-13 · vals.ai ↗
Leaderboard
Opus 5.5 max
More from this benchmark
1 published measuresTime per task109 results · lower is better
All results
62 rows| # | Model | Effort | MedScribe | Subscription $ / task | API $ / task | Time |
|---|---|---|---|---|---|---|
| 1 | Opus 5.5 | max | 91.4% | $0.017 | $1.15 | 7.4 min |
| 2 | Fable 5.1 | max | 91.3% | $0.15 | $0.96 | 3.1 min |
| 3 | Sonnet 5.5 | max | 91.1% | $0.008 | $0.51 | 5.1 min |
| 4 | Opus 5 | max | 91.0% | $0.004 | $0.24 | 77s |
| 5 | Muse Spark 1.2 | xhigh | 90.1% | $0.019 | $0.038 | 61s |
| 6 | Haiku 5.5 | max | 89.5% | $0.001 | $0.044 | 5.4 min |
| 7 | Grok 4.7 | xhigh | 89.4% | $0.007 | $0.075 | 2.6 min |
| 8 | GLM 5.3 Flash | max | 88.9% | free | $0.002 | 87s |
| 9 | Muse Spark 1.1 | xhigh | 88.9% | $0.035 | $0.035 | 63s |
| 10 | GLM 5.3 | max | 88.8% | $0.006 | $0.057 | 2.0 min |
| 11 | Fable 5 | max | 88.5% | $0.066 | $0.58 | 2.0 min |
| 12 | MiMo V2.6 Pro | high | 88.3% | $0.008 | $0.010 | 2.9 min |
| 13 | Kimi K3 | max | 88.0% | $0.009 | $0.11 | 38s |
| 14 | GPT-6 Astra | max | 87.9% | $0.050 | $0.58 | 2.6 min |
| 15 | Gemini 4 Argon | high | 87.4% | $0.052 | $0.15 | 87s |
| 16 | MiniMax M3 | max | 87.3% | $0.002 | $0.014 | 2.1 min |
| 17 | Grok 4.5 | high | 86.9% | $0.005 | $0.033 | 12 min |
| 18 | GPT-5.5 | xhigh | 86.9% | $0.008 | $0.14 | 2.2 min |
| 19 | Grok 4.6 | high | 86.5% | $0.004 | $0.037 | 71s |
| 20 | GPT-6.1 Sol | max | 86.5% | $0.012 | $0.10 | 2.8 min |
| 21 | Muse Spark | 85.9% | $0.008 | $0.008 | 3.2 min | |
| 22 | Opus 4.8 | max | 85.8% | $0.004 | $0.26 | 82s |
| 23 | DeepSeek V4.1 Flash | high | 85.5% | $0.001 | $0.015 | 54s |
| 24 | Inkling | max | 85.4% | free | $0.17 | 4.1 min |
| 25 | MiMo V2.6 Flash | high | 85.3% | free | $0.002 | 74s |
| 26 | GPT-5.6 Sol | max | 85.2% | $0.015 | $0.28 | 1.6 min |
| 27 | Qwen 3.8 Max | max | 84.9% | $0.090 | $0.090 | 4.2 min |
| 28 | Gemini 3.8 Flash | high | 84.5% | $0.001 | $0.025 | 21s |
| 29 | GPT-5.6 Luna | max | 84.4% | $0.002 | $0.023 | 1.9 min |
| 30 | Inkling Small | max | 84.1% | free | $0.019 | 3.8 min |