Benchmarks · knowledge
MedCode
Can models support the medical billing process?
60 models · 60 results · updated 2026-10-13 · vals.ai ↗
Leaderboard
Opus 5 max
More from this benchmark
1 published measuresTime per task107 results · lower is better
All results
60 rows| # | Model | Effort | MedCode | Subscription $ / task | API $ / task | Time |
|---|---|---|---|---|---|---|
| 1 | Opus 5 | max | 63.6% | $0.003 | $0.16 | 25s |
| 2 | Gemini 4 Argon | high | 58.8% | $0.049 | $0.14 | 80s |
| 3 | Fable 5 | max | 56.1% | $0.067 | $0.59 | 1.5 min |
| 4 | Gemini 3.5 Flash | high | 55.8% | $0.074 | $0.074 | 25s |
| 5 | Opus 4.7 | max | 54.9% | $0.23 | $0.23 | 54s |
| 6 | Fable 5.1 | max | 53.5% | $0.17 | $1.12 | 3.6 min |
| 7 | Gemini 3.7 Flash | high | 53.4% | $0.005 | $0.038 | 9.2s |
| 8 | Opus 4.8 | max | 53.2% | $0.006 | $0.35 | 1.8 min |
| 9 | Gemini 3.6 Flash | high | 53.2% | $0.001 | $0.044 | 17s |
| 10 | Sonnet 5.5 | max | 52.9% | $0.006 | $0.39 | 4.0 min |
| 11 | Haiku 5.5 | max | 51.5% | $0.001 | $0.032 | 3.8 min |
| 12 | Muse Spark | 51.3% | $0.005 | $0.005 | 2.1 min | |
| 13 | Gemini 2.5 Pro | high | 50.6% | $0.015 | $0.015 | 27s |
| 14 | Opus 5.5 | max | 49.8% | $0.010 | $0.66 | 4.1 min |
| 15 | Grok 4.7 | xhigh | 49.6% | $0.010 | $0.11 | 3.6 min |
| 16 | Kimi K3 | max | 49.4% | $0.007 | $0.094 | 37s |
| 17 | Muse Spark 1.2 | xhigh | 49.3% | $0.020 | $0.039 | 60s |
| 18 | GPT-5.5 | xhigh | 49.1% | $0.009 | $0.16 | 2.7 min |
| 19 | GPT-6.1 Sol | max | 48.8% | $0.010 | $0.085 | 1.9 min |
| 20 | GPT-6 Astra | max | 48.5% | $0.039 | $0.45 | 1.7 min |
| 21 | Gemini 3.8 Flash | high | 48.1% | $0.001 | $0.018 | 43s |
| 22 | Sonnet 5 | max | 47.5% | $0.005 | $0.28 | 2.2 min |
| 23 | GPT-6 Sol | max | 47.1% | $0.005 | $0.086 | 63s |
| 24 | MiniMax M3 | max | 46.3% | $0.002 | $0.012 | 63s |
| 25 | MiMo V2.6 Pro | high | 45.0% | $0.008 | $0.010 | 2.9 min |
| 26 | Grok 4.6 | high | 44.7% | $0.005 | $0.050 | 2.1 min |
| 27 | GPT-6 Luna | max | 44.7% | $0.001 | $0.007 | 1.8 min |
| 28 | GPT-5.6 Sol | max | 44.0% | $0.015 | $0.28 | 1.6 min |
| 29 | Gemini 3.5 Flash-Lite | high | 43.5% | $0.008 | $0.008 | 6.0s |
| 30 | GPT-5.6 Terra | xhigh | 43.4% | $0.003 | $0.047 | 18s |