RPCBench - Error Group - Boundary-Violating Premise - Conditional Strategy Quality: leaderboard

Metric: Strategy Quality (0-100). Source: github.com. Saturation forecast: Around December 2026. 11 models tracked.

Top models

#ModelScore
1Qwen 3.5 397B A17B95.23
2Qwen 3.5 Plus94.27
3Qwen 3.5 122B A10B91.05
4GPT-5.590.75
5Claude Sonnet 4.690.57
6Qwen 3.5 35B A3B90.4
7Gemini 3.1 Pro (Preview)89.37
8DeepSeek V4 Pro78.72
9DeepSeek V4 Flash77.99
10Llama 3.1 70B Instruct71.47
11Llama 3.1 8B Instruct63.78

Interactive version: theaggregate.ai/benchmark?slug=rpcbench-error-group-boundary-violating-premise-conditional-strategy-quality · How It Works · Data refreshed daily, snapshot 2026-09-24.