RPCBench - Domain - Amazon Sports - Composite Premise Critique: leaderboard
RPCBench tests proactive premise critique in recommendation requests. This series measures composite premise critique on the Amazon Sports subset (1,270 questions), using the same eleven-model, three-judge experiment as the headline paper. Published CPCC fractions from the authors' per-model CSV are scaled once to Composite Score (0-100). Higher is better; domains and nested premise-error groups are related slices of the same experiment.
Metric: Composite Score (0-100). Source: github.com. Saturation forecast: Around February 2027. 11 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | GPT-5.5 | 60.85 | #34 |
| 2 | Qwen 3.5 397B A17B | 59.84 | #155 |
| 3 | Claude Sonnet 4.6 | 59.6 | #97 |
| 4 | Qwen 3.5 Plus | 59.28 | #136 |
| 5 | Qwen 3.5 122B A10B | 56.81 | #186 |
| 6 | Gemini 3.1 Pro (Preview) | 55.13 | #66 |
| 7 | Qwen 3.5 35B A3B | 53.95 | #270 |
| 8 | DeepSeek V4 Pro | 52.3 | #113 |
| 9 | DeepSeek V4 Flash | 48.8 | #156 |
| 10 | Llama 3.1 70B Instruct | 19.56 | #570 |
| 11 | Llama 3.1 8B Instruct | 13.97 | #1021 |
No result here: #3 Claude Opus 5.5, #5 GPT-6 Astra, #6 GPT-6.1 Sol.
Interactive version: theaggregate.ai/benchmark?slug=rpcbench-domain-amazon-sports-composite-premise-critique · How It Works · Data refreshed daily, snapshot 2026-11-07.