RPCBench - Domain - MIND-small - Evidence Distortion: leaderboard
Metric: Evidence Distortion Rate (%). Source: github.com. Saturation forecast: Around June 2028. 11 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | GPT-5.5 | 19.63 |
| 2 | Llama 3.1 70B Instruct | 23.47 |
| 3 | Gemini 3.1 Pro (Preview) | 23.61 |
| 4 | Qwen 3.5 397B A17B | 24.75 |
| 5 | Qwen 3.5 122B A10B | 25.75 |
| 6 | Qwen 3.5 35B A3B | 25.89 |
| 7 | Llama 3.1 8B Instruct | 27.88 |
| 8 | Qwen 3.5 Plus | 27.88 |
| 9 | DeepSeek V4 Flash | 28.88 |
| 10 | Claude Sonnet 4.6 | 30.3 |
| 11 | DeepSeek V4 Pro | 30.3 |
Interactive version: theaggregate.ai/benchmark?slug=rpcbench-domain-mind-small-evidence-distortion · How It Works · Data refreshed daily, snapshot 2026-09-24.