RPCBench - Domain - MovieLens-1M - Composite Premise Critique: leaderboard
Metric: Composite Score (0-100). Source: github.com. Saturation forecast: Around March 2027. 11 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | DeepSeek V4 Pro | 49.27 |
| 2 | Qwen 3.5 122B A10B | 43.54 |
| 3 | Qwen 3.5 Plus | 43.4 |
| 4 | Qwen 3.5 397B A17B | 42.29 |
| 5 | Gemini 3.1 Pro (Preview) | 41.81 |
| 6 | Qwen 3.5 35B A3B | 35.87 |
| 7 | GPT-5.5 | 35.69 |
| 8 | DeepSeek V4 Flash | 35.63 |
| 9 | Claude Sonnet 4.6 | 33.93 |
| 10 | Llama 3.1 70B Instruct | 4.04 |
| 11 | Llama 3.1 8B Instruct | 2.53 |
Interactive version: theaggregate.ai/benchmark?slug=rpcbench-domain-movielens-1m-composite-premise-critique · How It Works · Data refreshed daily, snapshot 2026-09-24.