RPCBench - Domain - Yelp Local - Composite Premise Critique: leaderboard
Metric: Composite Score (0-100). Source: github.com. Saturation forecast: Around December 2026. 11 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Qwen 3.5 122B A10B | 60.95 |
| 2 | DeepSeek V4 Pro | 60.08 |
| 3 | Qwen 3.5 Plus | 59.82 |
| 4 | Qwen 3.5 397B A17B | 59.26 |
| 5 | GPT-5.5 | 58.62 |
| 6 | Gemini 3.1 Pro (Preview) | 57.68 |
| 7 | Qwen 3.5 35B A3B | 57.38 |
| 8 | Claude Sonnet 4.6 | 56.66 |
| 9 | DeepSeek V4 Flash | 55.42 |
| 10 | Llama 3.1 70B Instruct | 16.71 |
| 11 | Llama 3.1 8B Instruct | 10.39 |
Interactive version: theaggregate.ai/benchmark?slug=rpcbench-domain-yelp-local-composite-premise-critique · How It Works · Data refreshed daily, snapshot 2026-09-24.