RPCBench - Domain - MIND-small - Composite Premise Critique: leaderboard
Metric: Composite Score (0-100). Source: github.com. Saturation forecast: Around October 2027. 11 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Claude Sonnet 4.6 | 41.96 |
| 2 | DeepSeek V4 Pro | 41.49 |
| 3 | GPT-5.5 | 39.66 |
| 4 | Qwen 3.5 122B A10B | 39.01 |
| 5 | Qwen 3.5 Plus | 38.59 |
| 6 | Qwen 3.5 397B A17B | 38.24 |
| 7 | Gemini 3.1 Pro (Preview) | 38.07 |
| 8 | DeepSeek V4 Flash | 36.19 |
| 9 | Qwen 3.5 35B A3B | 35.13 |
| 10 | Llama 3.1 70B Instruct | 9.21 |
| 11 | Llama 3.1 8B Instruct | 6.33 |
Interactive version: theaggregate.ai/benchmark?slug=rpcbench-domain-mind-small-composite-premise-critique · How It Works · Data refreshed daily, snapshot 2026-09-24.