HealthAgentBench - CT Abnormality Classification: leaderboard
HealthAgentBench (2026) evaluates coding agents on healthcare tasks in terminal environments over real clinical data, at xhigh reasoning effort with web browsing disabled. This board is the task success rate in percent over three attempts at classifying abnormalities in 3D chest CT volumes, a trial succeeding only when every abnormality label is correct; higher is better.
Metric: 3D chest CT abnormality classification (10 tasks; success when every abnormality label is correct): task success rate (%) over three attempts per task, a trial succeeding only when it meets the category success criterion; terminal environments in the Harbor framework, xhigh reasoning effort, web browsing disabled. Source: arxiv.org. Saturation forecast: Around 2030. 10 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | GPT-5.5 (xHigh) | 33 | #49 (GPT-5.5) |
| 2 | GPT-5.4 (xHigh) | 30 | #123 (GPT-5.4) |
| 3 | GPT-5.4 Mini (xHigh) | 23 | #389 (GPT-5.4 Mini) |
| 4 | Claude Opus 4.8 (xHigh) | 17 | #56 (Claude Opus 4.8) |
| 5 | Claude Opus 4.7 (xHigh) | 13 | #79 (Claude Opus 4.7) |
| 6 | GPT-5.3 Codex (xHigh) | 10 | #116 (GPT-5.3 Codex) |
No result here: #1 Claude Fable 5.2, #2 Gemini 4 Carbon, #5 Claude Opus 5.5.
Interactive version: theaggregate.ai/benchmark?slug=healthagentbench-ct-abnormality-classification · How It Works · Data refreshed daily, snapshot 2026-11-13.