LogiMed-RoB - Verdict Reliability: leaderboard
Metric: Reliability (%). Source: arxiv.org. 10 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Claude Sonnet 4.5 | 100 |
| 2 | DeepSeek V3.2 | 100 |
| 3 | Llama 3.3 70B | 100 |
| 4 | Llama 4 Maverick | 99.84 |
| 5 | Gemini 3.1 Pro (Preview) | 99.64 |
| 6 | Qwen 3 32B | 99.36 |
| 7 | GPT-5.1 | 96.17 |
| 8 | Gemini 3 Flash | 94.24 |
Interactive version: theaggregate.ai/benchmark?slug=logimed-rob-verdict-reliability · How It Works · Data refreshed daily, snapshot 2026-09-21.