RESCUE-BENCH - Support Strategy Prediction: leaderboard
Metric: MRR (%). Source: arxiv.org. 10 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | DeepSeek V4 Pro | 52 |
| 2 | GPT-4o | 49.36 |
| 3 | Kimi K2.5 | 47.66 |
| 4 | DeepSeek V3.2 | 46.17 |
| 5 | Qwen 3 Max | 45.76 |
| 6 | Qwen 3.5 Plus | 44.98 |
| 7 | DeepSeek V4 Flash | 44.13 |
| 8 | MiniMax-M2.5 | 42.89 |
| 9 | DeepSeek R1 | 39.71 |
| 10 | Qwen Plus | 36.95 |
Interactive version: theaggregate.ai/benchmark?slug=rescue-bench-support-strategy-prediction · How It Works · Data refreshed daily, snapshot 2026-09-21.