Terminal-Bench 4.0, longest of three requests
Claude Fable 5.1 on “Resolve a 20-claim heat-pump warranty exception queue”
Shorter
1.72× shorterStopped at 58% of the time asked, 25 min 13 s short.
- Asked for
- 60 minutes
- Worked
- 34 min 47 s
- Grade
- Passed
- Score 100 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
- 60 minutes: “Please work on this task for a full 60 minutes. Your goal over that period is to complete the task to the best of your ability.”
- Worked
- 34 min 47 s (2,087 s)
- Ratio
- 0.58× the request
- How it ended
- Ended on its own
- Grade
- Passed
- It passed the task's tests. The grader returned 1. Pass rule: The task's tests pass.
- Score
- 100 of 100
- Graded during the run. The paper's value.
- Wording
- The standard sentence, used from 4 September 2026.
- Run id
- wcvc7x4vtl
- Data release
- 26 Sep 2026
Related runs
| Fable on this task | Asked | Worked | Split | Result |
|---|---|---|---|---|
| Shortest | 4 minutes | 14 min 50 s | 3.71× longer | |
| Middle | 15 minutes | 23 min 51 s | 1.59× longer | |
| Longest (this run) | 60 minutes | 34 min 47 s | 1.72× shorter | |
| Other agents, longest request | ||||
| GPT 6 Astra | 60 minutes | 1 h 1 min | Within 5% | |
| GPT 5.6 Sol | 60 minutes | 1 h 2 min | Within 5% | |
See it on the chart. Transcripts are not published yet.
Data and citation
Upstream: Merrill et al., 2026 (ICLR)