WildClawBench
Progress Over Time
Interactive timeline showing model performance evolution on WildClawBench
State-of-the-art frontier
Open
Proprietary
WildClawBench Leaderboard
6 models
| Context | Cost | License | ||||
|---|---|---|---|---|---|---|
| 1 |  Alibaba Cloud / Qwen Team | — | — | — | ||
| 2 |  ByteDance | — | — | — | ||
| 3 | ByteDance | — | — | — | ||
| 4 |  Tencent | 295B | 262K | $0.14 / $0.58 | ||
| 5 |  Meta | 30B | 131K | $0.30 / $1.20 | ||
| 6 |  Xiaomi | 1.0T | 1.0M | $0.43 / $0.87 |
Notice missing or incorrect data?
What is WildClawBench?
WildClawBench is an agentic coding benchmark from InternLM/Claw-Eval that reports overall model performance on real-world tool-using development tasks.
WildClawBench is a text benchmark evaluating models on agents and coding tasks. LLM Stats tracks 6 models on this benchmark, scored on a 0–1 scale. The current average is 0.6, with the leader at 0.7.
Compare leaders on the best AI for agents and best AI for coding leaderboards.
Current leaders
Qwen3.8 Omni Flash from Alibaba Cloud / Qwen Team currently leads the WildClawBench leaderboard with a score of 0.710 across 6 evaluated AI models.
FAQ
Common questions about the WildClawBench benchmark and leaderboard.