GLM-5
by Z-AI, Z.ai
72.8
best score
72.8%
Best Score
bash-only
Best Leaderboard
1
Models Used
Yes
Open Source
Score History
| Entry | Score |
|---|---|
| GLM-5 (high reasoning) | 72.8% |
| mini-SWE-agent + GLM-5 (high reasoning) | 72.8% |
| GLM-5 | 69.7% |
| GLM-4.6 (T=1) | 55.4% |
| GLM-4.6 | 68.2% |
| GLM-4.5 (2025-08-22) | 54.2% |
| GLM-4.5 | 64.2% |