WildClawBench
WildClawBench - agentic coding evaluation benchmark. Overall score from internlm/WildClawBench.
Category
Agentic Coding
Max Score
100.0
Score Type
percent
Active
Yes
Model Scores
Scores for WildClawBench
| Model | Score | Date | Verified |
|---|---|---|---|
| Muse-Glimmer-30B |
63.38%
|
01.08.2026 | Verified |
| Gemma4-31B-it |
48.68%
|
01.08.2026 | Unverified |
| Qwen3.6-27B |
56.91%
|
01.08.2026 | Unverified |
| Kimi K3 |
73.53%
|
18.08.2026 | Verified |
| GLM-5.2 |
73.09%
|
17.06.2026 | Verified |
| Ornith-1.0-35B-A3B |
96.03%
|
19.08.2026 | Unverified |
| Qwen3.6-35B-A3B |
94.41%
|
19.08.2026 | Unverified |
| Gemma-4-31B |
64.71%
|
19.08.2026 | Unverified |
| Qwen3.5-397B-A17B |
97.35%
|
19.08.2026 | Unverified |
| Kimi K2.7 Code |
62.35%
|
23.08.2026 | Unverified |
| MiniCPM5-2B |
28.53%
|
— | Verified |
| LFM2.5-2.6B |
8.38%
|
— | Verified |
| Qwen3.5-2B |
6.91%
|
— | Verified |
| Gemma4-E2B |
6.47%
|
— | Verified |
| Qwen3.5-4B |
18.38%
|
— | Verified |
| Nemotron-3-Nano-4B |
6.47%
|
— | Verified |
| Gemma4-E4B |
14.41%
|
— | Verified |
| Ornith-1.5-35B-A3B |
100.00%
|
19.08.2026 | Verified |
| granite-4.2-3B |
22.79%
|
— | Verified |
| LFM2.5-8B-A1B |
4.50
|
— | Verified |