LiveClawBench: leaderboard
Metric: Average reward (0-100) over three runs on all 134 cases, OpenClaw-style personal-assistant tasks run in reproducible full-stack mock services (22 stateful web applications, browser, APIs and shell), three runs per case, rewards from case verifiers and a DeepSeek-V3.2 rubric judge for open-ended cases; higher is better. Source: arxiv.org. Saturation forecast: Around January 2027. 17 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Kimi K2.7 Code | 76 |
| 2 | GLM-5.1 | 74.7 |
| 3 | GPT-5.5 | 74.5 |
| 4 | GLM-5.2 | 72.9 |
| 5 | MiniMax-M3 | 71.4 |
| 6 | Qwen 3.6 Plus | 70.6 |
| 7 | MiMo-V2.5-Pro | 70.6 |
| 8 | Qwen 3.6 Flash | 70.2 |
| 9 | Claude Opus 4.8 | 68.8 |
| 10 | Kimi K2.6 | 68.6 |
| 11 | MiniMax-M2.7 | 68.4 |
| 12 | DeepSeek V4 Pro | 65.6 |
| 13 | DeepSeek V4 Flash | 60.5 |
| 14 | Qwen 3.5 Plus | 57 |
| 15 | Qwen 3.6 27B | 54.5 |
Interactive version: theaggregate.ai/benchmark?slug=liveclawbench · How It Works · Data refreshed daily, snapshot 2026-10-07.