LiveClawBench - Pass@3: leaderboard
Agent reliability on LiveClawBench (2026), personal-assistant agent tasks in reproducible full-stack mock services (stateful web applications, browser, APIs and shell) with implicit goals and runtime perturbations, three runs per case scored by case verifiers and a rubric judge. Share of the 134 cases in which at least one of the three runs earns a reward above 0.8, in percent; higher is better.
Metric: Pass@3 (x100): share of the 134 cases where at least one of three runs has reward above 0.8, 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 February 2027. 17 models tracked. Updated 7 Oct 2026.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Kimi K2.7 Code | 70.9 | #203 |
| 2 | GLM-5.1 | 69.4 | #198 |
| 3 | MiniMax-M3 | 68.7 | #280 |
| 4 | GPT-5.5 | 67.9 | #54 |
| 5 | DeepSeek V4 Pro | 67.9 | #196 |
| 6 | MiniMax-M2.7 | 66.4 | #539 |
| 7 | GLM-5.2 | 66.4 | #150 |
| 8 | Kimi K2.6 | 65.4 | #192 |
| 9 | Qwen 3.6 Flash | 64.2 | #448 |
| 10 | Qwen 3.6 Plus | 63.4 | #238 |
| 11 | MiMo-V2.5-Pro | 63.4 | #284 |
| 12 | Claude Opus 4.8 | 61.9 | #65 |
| 13 | DeepSeek V4 Flash | 61.9 | #267 |
| 14 | Qwen 3.5 Plus | 59.7 | #242 |
| 15 | Qwen 3.6 27B | 58.2 | #351 |
No result here: #1 Claude Fable 5.2, #3 Gemini 4 Neon, #4 GPT-6.2 Astra.
Interactive version: theaggregate.ai/benchmark?slug=liveclawbench-pass-3 · How It Works · Data refreshed daily, snapshot 2026-11-21.