RPCBench - Domain - Goodreads Dual-Domain - Composite Premise Critique: leaderboard
Metric: Composite Score (0-100). Source: github.com. Saturation forecast: Around April 2027. 11 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Qwen 3.5 397B A17B | 49.02 |
| 2 | Qwen 3.5 122B A10B | 48.82 |
| 3 | Qwen 3.5 Plus | 48.26 |
| 4 | DeepSeek V4 Pro | 47.52 |
| 5 | Gemini 3.1 Pro (Preview) | 47.36 |
| 6 | GPT-5.5 | 46.54 |
| 7 | Claude Sonnet 4.6 | 45.88 |
| 8 | Qwen 3.5 35B A3B | 44.69 |
| 9 | DeepSeek V4 Flash | 44.05 |
| 10 | Llama 3.1 8B Instruct | 11.47 |
| 11 | Llama 3.1 70B Instruct | 8.68 |
Interactive version: theaggregate.ai/benchmark?slug=rpcbench-domain-goodreads-dual-domain-composite-premise-critique · How It Works · Data refreshed daily, snapshot 2026-09-24.