Public KG record
Terminal-Bench 4
Recorded overview
Evaluation benchmark for coding agent harnesses; Factory runs 3 trials per task,
An evidence-backed entity from the project knowledge graph; detailed tool metadata is still being added.
Recorded details
- Benchmarks: Mistral Large 4 得分 28.3%
- Benchmarks: 每任务 3 次试验，2026 年 10 月 23 至 28 日运行
Evidence coverage
The KG currently records 6 known information dimensions and has 12 undocumented dimensions, linked to 3 public source articles. These counts describe record coverage, not model performance or verified fit.
Related public records
- Droid 1.0 — evaluated on
- Mistral Large 4 — evaluated on
- SWE-2 — evaluated on