LogiMed-RoB - Condition-Aware Ratio: leaderboard
Risk-of-bias judgements on clinical trials: the atomic-level condition-aware ratio, averaged over the scored RoB 2.0 domains. Higher is better. Source: arxiv.org/abs/2609.11185.
Metric: Ratio (%). Source: arxiv.org. Saturation forecast: Estimated already saturated. 10 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Gemini 3.1 Pro (Preview) | 98.88 | #64 |
| 2 | Gemini 3 Flash | 98.85 | #103 |
| 3 | GPT-5.1 | 98.34 | #145 |
| 4 | Claude Sonnet 4.5 | 97.2 | #148 |
| 5 | DeepSeek V3.2 | 92.01 | #210 |
| 6 | Qwen 3 32B | 80.83 | #449 |
| 7 | Llama 4 Maverick | 73 | #486 |
| 8 | Llama 3.3 70B | 68.18 | #578 |
No result here: #3 Claude Opus 5.5, #6 GPT-6 Astra, #7 GPT-6.1 Sol.
Interactive version: theaggregate.ai/benchmark?slug=logimed-rob-condition-aware-ratio · How It Works · Data refreshed daily, snapshot 2026-11-05.