RPCBench - Domain - Goodreads Dual-Domain - Evidence Distortion: leaderboard
Metric: Evidence Distortion Rate (%). Source: github.com. Saturation forecast: Around January 2028. 11 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Gemini 3.1 Pro (Preview) | 16.74 |
| 2 | GPT-5.5 | 18 |
| 3 | Claude Sonnet 4.6 | 22.55 |
| 4 | Qwen 3.5 397B A17B | 22.78 |
| 5 | Qwen 3.5 Plus | 22.89 |
| 6 | Qwen 3.5 122B A10B | 23.01 |
| 7 | Llama 3.1 8B Instruct | 24.94 |
| 8 | DeepSeek V4 Pro | 25.17 |
| 9 | DeepSeek V4 Flash | 25.17 |
| 10 | Qwen 3.5 35B A3B | 25.63 |
| 11 | Llama 3.1 70B Instruct | 25.74 |
Interactive version: theaggregate.ai/benchmark?slug=rpcbench-domain-goodreads-dual-domain-evidence-distortion · How It Works · Data refreshed daily, snapshot 2026-09-24.