CLBench - Rule System Application: leaderboard
Metric: Solving Rate (%). Source: www.clbench.com. 36 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | GPT-5.4 (xHigh) | 26.7 |
| 2 | GPT-5.1 (High) | 23.7 |
| 3 | Grok 4.20 (Reasoning) | 22.7 |
| 4 | Hy3-preview | 21.6 |
| 5 | Claude Opus 4.6 | 21.4 |
| 6 | GPT-5.1 | 21 |
| 7 | Seed 2.0 Pro (High) | 20.7 |
| 8 | Gemini 3.1 Pro (Preview) (High) | 20.2 |
| 9 | Qwen 3.6 Plus | 19.6 |
| 10 | Seed 2.0 Pro (Medium) | 19.3 |
| 11 | Claude Opus 4.5 | 19.1 |
| 12 | Claude Opus 4.5 (Thinking) | 19 |
| 13 | Qwen 3.5 Plus (Thinking) | 18.9 |
| 14 | GPT-5.2 | 18 |
| 15 | Kimi K2.5 | 17.9 |
Interactive version: theaggregate.ai/benchmark?slug=clbench-rule-system-application · How It Works · Data refreshed daily, snapshot 2026-09-19.