BrainTRACE - L1 Abnormality: leaderboard
Paper2610.06571v1 Table3; GPT4o-mini-2024-07-18 factual judge; all required facts/critical slots, no critical errors/unsupported claims. Open Broad1597,3D77; case420steps in70six-step cases. Missing predictions excluded from scored denominator; empty/refusal/judge-retry failure fails if scored. Track/model image limits vary; public metadata, MRI images require access. Source-compatible physician MCQ sample is not a model row. Exact medium/thinking settings bound by companion run manifest; disputed closed-form scores withheld.
Metric: Clinical rubric pass (%). Source: arxiv.org. Saturation forecast: Around 2032. 10 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | GPT-5.4 (Medium) | 24.5 | #83 (GPT-5.4) |
| 2 | Claude Opus 4.6 | 22 | #67 |
| 3 | Gemini 2.5 Pro | 20.5 | #159 |
| 4 | Qwen 3.5 27B (Thinking) | 17.5 | #192 (Qwen 3.5 27B) |
| 5 | GPT-5 Mini | 16 | #193 |
| 6 | MedGemma-4B-IT | 15.5 | #811 |
| 7 | GPT-5 | 15 | #105 |
No result here: #3 Claude Opus 5.5, #6 GPT-6 Astra, #7 GPT-6.1 Sol.
Interactive version: theaggregate.ai/benchmark?slug=braintrace-l1-abnormality · How It Works · Data refreshed daily, snapshot 2026-11-05.