Benchmarks / SuperCLUE-XClaw
SuperCLUE-XClaw: results for personal AI agents
SuperCLUE-XClaw is published by SuperCLUE (CN). It reports 0–100 weighted total of 5 dimensions. 10 personal AI agent products have a published score (source updated 4 Aug 2026, retrieved by PAEval 9 Oct 2026). Overlap with other evaluators: 0 products shared with Assistant Benchmark; 0 products shared with micro1 PersonalAgentBench.
What it measures
Five task dimensions (code development, content creation, data processing, research & analysis, memory). Deliverable-based tasks set by SuperCLUE; answers collected manually and assessed automatically; three independent runs, published score is the mean of three runs. Products within 1 point are ranked as tied by the publisher.
How to read it
- Batches differ in products, product versions and possibly task sets; scores are not comparable across batches.
- Chinese-language tasks; products evaluated are predominantly mainland-China Claw-style agents.
- Ceiling effects: content creation and memory are near 100 for most products in Aug 2026, limiting discrimination.
- Per-run scores exist on the source page but were not captured; no confidence intervals are published.
- ArkClaw (Aug 2026), ArkClaw-Pro and ArkClaw-Lite (Mar 2026) are kept as separate entries; the source does not state which tier the August entry tested.
- QwenPaw (Aug) and CoPaw (Mar) are both Alibaba entries but are not merged without an official statement that one replaced the other.
- MaxClaw is not merged with the MiniMax Agent work-mode profile; AutoClaw is not merged with the AutoGLM hosted application profile.
Published results
| Source rank | Product | Score | Detail |
|---|---|---|---|
| 1 | Wenxin Assistant (task mode)Baidu | 97.62 | coverage 5/5 |
| 1 | MiMoClawXiaomi | 96.74 | coverage 5/5 |
| 2 | WorkBuddy (Tencent)Tencent | 96.61 | coverage 5/5 |
| 2 | KimiClawMoonshot AI | 96.01 | coverage 5/5 |
| 3 | MaxClawMiniMax | 94.79 | coverage 5/5 |
| 4 | DuMateBaidu | 93.44 | coverage 5/5 |
| 4 | AutoClawZhipu AI | 93.23 | coverage 5/5 |
| 4 | QwenPawAlibaba | 92.97 | coverage 5/5 |
| 4 | ArkClawByteDance | 92.61 | coverage 5/5 |
| 5 | StepClawStepFun | 91.31 | coverage 5/5 |
Values copied from the publisher on its own scale. Full charts and per-dimension tables are on the leaderboards page.