Claw-Eval-Live: leaderboard
Quarterly refreshed enterprise-workflow benchmark grounded in live ClawHub marketplace signals and scored with deterministic checks plus structured judging.
Metric: Pass Rate (self-reported). Source: benchmarklist.com. Status: saturation imminent. 13 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Claude Opus 4.6 | 66.7 |
| 2 | GPT-5.4 | 63.8 |
| 3 | Claude Sonnet 4.6 | 61.9 |
| 4 | GLM-5 | 61.9 |
| 5 | MiniMax-M2.7 | 54.3 |
| 6 | Gemini 3.1 Pro (Preview) | 53.3 |
| 7 | Kimi K2.5 | 53.3 |
| 8 | MiMo-V2-Pro | 53.3 |
| 9 | DeepSeek V3.2 | 51.4 |
| 10 | Qwen 3.6 Plus | 50.5 |
| 11 | MiniMax-M2.5 | 50.5 |
| 12 | Qwen 3.5 397B A17B | 49.5 |
Interactive version: theaggregate.ai/benchmark?slug=claw-eval-live · How It Works · Data refreshed daily, snapshot 2026-09-05.