Claw-Eval
Progress Over Time
Interactive timeline showing model performance evolution on Claw-Eval
State-of-the-art frontier
Open
Proprietary
Claw-Eval Leaderboard
14 models
| Context | Cost | License | ||||
|---|---|---|---|---|---|---|
| 1 |  Moonshot AI | 1.0T | 262K | $0.75 / $3.50 | ||
| 2 |  Zhipu AI | — | — | — | ||
| 3 |  MiniMax | 428B | 1.0M | $0.30 / $1.20 | ||
| 4 |  Tencent | 295B | — | — | ||
| 5 |  Alibaba Cloud / Qwen Team | — | 1.0M | $1.25 / $3.75 | ||
| 6 |  Xiaomi | 1.0T | 1.0M | $0.43 / $0.87 | ||
| 7 | Xiaomi | 311B | 1.0M | $0.17 / $0.34 | ||
| 8 |  Liquid AI | 3B | — | — | ||
| 9 | Alibaba Cloud / Qwen Team | — | — | — | ||
| 10 | Xiaomi | 1.0T | — | — | ||
| 11 | Alibaba Cloud / Qwen Team | 28B | 262K | $0.60 / $3.60 | ||
| 12 | Alibaba Cloud / Qwen Team | — | 1.0M | $0.50 / $3.00 | ||
| 13 | Xiaomi | — | — | — | ||
| 14 | Alibaba Cloud / Qwen Team | 35B | — | — |
Notice missing or incorrect data?
Sub-benchmarks
What is Claw-Eval?
Claw-Eval tests real-world agentic task completion across complex multi-step scenarios, evaluating a model's ability to use tools, navigate environments, and complete end-to-end tasks autonomously.
Claw-Eval is a text benchmark evaluating models on agents and code tasks. LLM Stats tracks 14 models on this benchmark, scored on a 0–1 scale. The current average is 0.6, with the leader at 0.8.
Compare leaders on the best AI for agents and best AI for code leaderboards.
Current leaders
Kimi K2.6 from Moonshot AI currently leads the Claw-Eval leaderboard with a score of 0.809 across 14 evaluated AI models.
FAQ
Common questions about the Claw-Eval benchmark and leaderboard.