RPCBench - Domain - MovieLens-1M - Evidence Distortion: leaderboard
Metric: Evidence Distortion Rate (%). Source: github.com. Saturation forecast: Around 2029. 11 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Llama 3.1 8B Instruct | 23.59 |
| 2 | Llama 3.1 70B Instruct | 32.47 |
| 3 | Gemini 3.1 Pro (Preview) | 33.55 |
| 4 | Qwen 3.5 Plus | 34.42 |
| 5 | Qwen 3.5 35B A3B | 34.63 |
| 6 | Qwen 3.5 397B A17B | 35.06 |
| 7 | Qwen 3.5 122B A10B | 35.06 |
| 8 | GPT-5.5 | 36.36 |
| 9 | DeepSeek V4 Pro | 38.96 |
| 10 | Claude Sonnet 4.6 | 40.26 |
| 11 | DeepSeek V4 Flash | 40.91 |
Interactive version: theaggregate.ai/benchmark?slug=rpcbench-domain-movielens-1m-evidence-distortion · How It Works · Data refreshed daily, snapshot 2026-09-24.