RPCBench - Domain - MIND-small - Conditional Strategy Quality: leaderboard
Metric: Strategy Quality (0-100). Source: github.com. Saturation forecast: Around December 2026. 11 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | DeepSeek V4 Pro | 81.96 |
| 2 | DeepSeek V4 Flash | 80.73 |
| 3 | Qwen 3.5 397B A17B | 79.78 |
| 4 | Claude Sonnet 4.6 | 79.17 |
| 5 | Qwen 3.5 Plus | 78.9 |
| 6 | Qwen 3.5 122B A10B | 78.81 |
| 7 | Qwen 3.5 35B A3B | 78.62 |
| 8 | GPT-5.5 | 72.29 |
| 9 | Gemini 3.1 Pro (Preview) | 72.25 |
| 10 | Llama 3.1 70B Instruct | 58.47 |
| 11 | Llama 3.1 8B Instruct | 52.33 |
Interactive version: theaggregate.ai/benchmark?slug=rpcbench-domain-mind-small-conditional-strategy-quality · How It Works · Data refreshed daily, snapshot 2026-09-24.