Run #129
Claude Code running glm-4.7.
33.3%95% interval 25.2–41.6%
Details
What the site recorded for this run. This address keeps pointing at it.
- Entry
claudecode-glm-4-7- Model
glm-4.7- Date
- 7 Feb 2026
- hbench release
- converted from another tool's job
- hbench results epoch
- 0.2
Cite this run
Claude Code (claude-code, entry claudecode-glm-4-7), Terminal-Bench 2.0 on GLM-4.7 (5 attempts, open network): 33.3% (95% interval 25.2–41.6%), run #129, 7 Feb 2026. https://nodeq.tech/runs/129
148 / 445trials solved
$2.33cost per solved trial
$345total cost
3.8 minmedian agent time
653.0M/3.8Mtokens in / out
By category
The share of trials solved in each kind of task.
- software-engineering48 / 130
- system-administration24 / 45
- data-science7 / 40
- scientific-computing8 / 40
- security20 / 40
- debugging10 / 25
- file-operations0 / 25
- data-processing11 / 20
- mathematics1 / 20
- model-training4 / 20
- machine-learning5 / 15
- data-querying0 / 5
- games0 / 5
- optimization5 / 5
- personal-assistant5 / 5
- video-processing0 / 5