RPCBench - Domain - MIND-small - Proactive Detection: leaderboard
Metric: Detection Rate (%). Source: github.com. Saturation forecast: Around July 2027. 11 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | GPT-5.5 | 49.79 |
| 2 | Claude Sonnet 4.6 | 49.5 |
| 3 | Gemini 3.1 Pro (Preview) | 49.22 |
| 4 | DeepSeek V4 Pro | 48.51 |
| 5 | Qwen 3.5 122B A10B | 46.66 |
| 6 | Qwen 3.5 Plus | 46.51 |
| 7 | Qwen 3.5 397B A17B | 46.09 |
| 8 | DeepSeek V4 Flash | 42.82 |
| 9 | Qwen 3.5 35B A3B | 42.25 |
| 10 | Llama 3.1 70B Instruct | 16.79 |
| 11 | Llama 3.1 8B Instruct | 12.23 |
Interactive version: theaggregate.ai/benchmark?slug=rpcbench-domain-mind-small-proactive-detection · How It Works · Data refreshed daily, snapshot 2026-09-24.