RPCBench - Error Group - Underspecified Premise - Conditional Strategy Quality: leaderboard
Metric: Strategy Quality (0-100). Source: github.com. Saturation forecast: Around 2030. 11 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Gemini 3.1 Pro (Preview) | 67.33 |
| 2 | Qwen 3.5 397B A17B | 66.93 |
| 3 | Qwen 3.5 35B A3B | 66.34 |
| 4 | DeepSeek V4 Pro | 64.72 |
| 5 | Claude Sonnet 4.6 | 63.4 |
| 6 | Qwen 3.5 122B A10B | 63.19 |
| 7 | Qwen 3.5 Plus | 62.86 |
| 8 | DeepSeek V4 Flash | 62.85 |
| 9 | GPT-5.5 | 58.26 |
| 10 | Llama 3.1 70B Instruct | 58 |
| 11 | Llama 3.1 8B Instruct | 53.85 |
Interactive version: theaggregate.ai/benchmark?slug=rpcbench-error-group-underspecified-premise-conditional-strategy-quality · How It Works · Data refreshed daily, snapshot 2026-09-24.