SIN-Bench - SIN-Find: leaderboard
Metric: Evidence Discovery Score (%; mean of evidence matching, relevance F1 and Kendall-tau logic). Source: arxiv.org. Saturation forecast: Around 2031. 8 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Claude Sonnet 4.5 (Thinking) | 46 |
| 2 | Gemini 3 Pro (Preview) | 39.9 |
| 3 | GPT-5 | 37.8 |
| 4 | Grok 4 | 37.8 |
| 5 | Qwen 3 VL 30B A3B (Thinking) | 35.2 |
| 6 | Gemini 2.5 Pro | 34.6 |
| 7 | Qwen 3 VL 8B (Thinking) | 34.6 |
Interactive version: theaggregate.ai/benchmark?slug=sin-bench-sin-find · How It Works · Data refreshed daily, snapshot 2026-09-25.