LiveClawBench - Hard: leaderboard
Agent performance on the 19 Hard cases of LiveClawBench (2026), personal-assistant agent tasks in reproducible full-stack mock services; a case is Hard when the anchor model DeepSeek-V4-Pro earns a mean reward of 0.3 or less on it. Average reward over three runs, from 0 to 100; higher is better.
Metric: Average reward (0-100) over three runs on the 19 Hard cases (DeepSeek-V4-Pro anchor reward 0.3 or less), 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 2028. 16 models tracked. Updated 7 Oct 2026.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | GLM-5.1 | 27.7 | #198 |
| 2 | Kimi K2.7 Code | 25.9 | #203 |
| 3 | MiniMax-M3 | 25.7 | #280 |
| 4 | GLM-5.2 | 24.3 | #150 |
| 5 | GPT-5.5 | 22 | #54 |
| 6 | MiniMax-M2.7 | 19.5 | #539 |
| 7 | Kimi K2.6 | 18.3 | #192 |
| 8 | MiMo-V2.5-Pro | 17.2 | #284 |
| 9 | Qwen 3.6 Flash | 14.3 | #448 |
| 10 | Qwen 3.6 Plus | 13.2 | #238 |
| 11 | DeepSeek V4 Flash | 13 | #267 |
| 12 | Qwen 3.5 Plus | 12.8 | #242 |
| 13 | Claude Opus 4.8 | 10.2 | #65 |
| 14 | Qwen 3.5 Flash | 5 | #441 |
| 15 | Qwen 3.6 27B | 4.7 | #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-hard · How It Works · Data refreshed daily, snapshot 2026-11-21.