ZClawBench
ZClawBench evaluates Claw-style agent task execution quality, measuring a model's ability to autonomously complete complex multi-step coding tasks in real-world environments.
3rows
scoreprimary metric
2026-05-06sampled
Metadata
Metrics
Score, Normalized Score
| Rank | Subject | Score | Model Match | Provenance | Sampled |
|---|---|---|---|---|---|
| 1 | GLM-5V-Turbo | 0.58 | GLM 5V Turbo z-ai-glm-5v-turbo | Self-reported | 2026-05-06 |
| 2 | Qwen3.6-27B | 0.53 |  Qwen3.6 27B qwen-qwen3.6-27b | Self-reported | 2026-05-06 |
| 3 | Qwen3.6-35B-A3B | 0.53 | Qwen3.6 35B A3B qwen-qwen3.6-35b-a3b | Self-reported | 2026-05-06 |
No matching rows.