Terminal-Bench 4.0, longest of three requests
Claude Fable 5.1 on “Port an Excel/VBA service-desk app to React, FastAPI, and SQLite”
Shorter
3.70× shorterStopped at 27% of the time asked, 1 h 49 min short.
- Asked for
- 150 minutes
- Worked
- 40 min 33 s
- Grade
- Did not pass
- Score 0 of 100. Graded during the run.
- How it ended
- Ended on its own
Every detail of this run
- Agent
- Claude Fable 5.1, in Claude Code
- Benchmark
- Terminal-Bench 4.0
- Asked for
- 150 minutes: “Please work on this task for a full 150 minutes. Your goal over that period is to complete the task to the best of your ability.”
- Worked
- 40 min 33 s (2,433 s)
- Ratio
- 0.27× the request
- How it ended
- Ended on its own
- Grade
- Did not pass
- It did not pass the task's tests. The grader returned 0. Pass rule: The task's tests pass.
- Score
- 0 of 100
- Graded during the run. The paper's value.
- Wording
- The standard sentence, used from 4 September 2026.
- Run id
- kvxsw43xg7
- Data release
- 26 Sep 2026
Related runs
| Fable on this task | Asked | Worked | Split | Result |
|---|---|---|---|---|
| Shortest | 10 minutes | 28 min | 2.80× longer | |
| Middle | 40 minutes | 27 min 39 s | 1.45× shorter | |
| Longest (this run) | 150 minutes | 40 min 33 s | 3.70× shorter | |
| Other agents, longest request | ||||
| GPT 6 Astra | 150 minutes | 2 h 31 min | Within 5% | |
| GPT 5.6 Sol | 150 minutes | 2 h 31 min | Within 5% | |
See it on the chart. Transcripts are not published yet.
Data and citation
Upstream: Merrill et al., 2026 (ICLR)