Benchmarks · agentic
DAYJOB: Healthcare
Uses Surge AI's rubric-graded healthcare assignment success rate. Score: score. Collected by Jake Boggs' benchmark dashboard.
35 models · 35 results · data as of 2026-10-29 · surgehq.ai ↗
Leaderboard
Opus 5.5 max
All results
35 rows| # | Model | Effort | DAYJOB: Healthcare |
|---|---|---|---|
| 1 | Opus 5.5 | max | 24.7% |
| 2 | Muse Wonder (Max) | max | 18.0% |
| 3 | Sonnet 5.5 | max | 15.2% |
| 4 | GPT-6 Astra | max | 11.6% |
| 5 | Gemini 4 Argon | high | 10.8% |
| 6 | Fable 5.1 | max | 9.6% |
| 7 | Opus 5 | max | 8.4% |
| 8 | Grok 4.7 | xhigh | 8.4% |
| 9 | Muse Spark 1.3 | max | 7.8% |
| 10 | GPT-6.1 Sol | max | 7.6% |
| 11 | Fable 5 | max | 5.6% |
| 12 | GPT-6 Sol | max | 3.6% |
| 13 | Grok 4.6 | xhigh | 2.8% |
| 14 | Mistral Large 4 | high | 2.0% |
| 15 | Muse Spark 1.2 | max | 2.0% |
| 16 | Qwen 3.8 Max | max | 2.0% |
| 17 | GPT-5.6 Sol | max | 1.6% |
| 18 | GPT-5.6 Terra | xhigh | 1.6% |
| 19 | Kimi K3 | max | 1.2% |
| 20 | Gemini 3.8 Flash | high | 0.8% |
| 21 | Hy4 | high | 0.8% |
| 22 | DeepSeek V4 Pro | max | 0.4% |
| 23 | GLM 5.3 Flash | max | 0.4% |
| 24 | GLM 5.3 | max | 0.4% |
| 25 | GPT-5.6 Luna | max | 0.4% |
| 26 | Hy3 | high | 0.4% |
| 27 | Nemotron 3 Ultra 550B A55B | max | 0.0% |
| 28 | Sonnet 5 | max | 0.0% |
| 29 | DeepSeek V4 Flash | max | 0.0% |
| 30 | Gemini 3.1 Pro | high | 0.0% |