RPCBench - Domain - MIND-small - Proactive Detection: leaderboard

Metric: Detection Rate (%). Source: github.com. Saturation forecast: Around July 2027. 11 models tracked.

Top models

#ModelScore
1GPT-5.549.79
2Claude Sonnet 4.649.5
3Gemini 3.1 Pro (Preview)49.22
4DeepSeek V4 Pro48.51
5Qwen 3.5 122B A10B46.66
6Qwen 3.5 Plus46.51
7Qwen 3.5 397B A17B46.09
8DeepSeek V4 Flash42.82
9Qwen 3.5 35B A3B42.25
10Llama 3.1 70B Instruct16.79
11Llama 3.1 8B Instruct12.23

Interactive version: theaggregate.ai/benchmark?slug=rpcbench-domain-mind-small-proactive-detection · How It Works · Data refreshed daily, snapshot 2026-09-24.