Terminal-Bench (Hard)
Frontier
Hard subset of Terminal-Bench - long-horizon shell + filesystem tasks.
- Publisher
- Laude Institute
- Published
- May 2026
- Canonical
- tbench.ai
Cite
Notes
Only stored in your browser.
Top score 65.9% by GPT-5.6 Sol - 332 models reporting (70 frontier)
Score history
332Top models
332
FAQ
- What is Terminal-Bench (Hard)?
- Hard subset of Terminal-Bench - long-horizon shell + filesystem tasks.
- What is the current top score on Terminal-Bench (Hard)?
- The top reported score is 65.9% by GPT-5.6 Sol, across 332 models reporting (70 from frontier labs).