Terminal-Bench 4.0, shortest of three requests
Claude Fable 5.1 on “Repair a React lead form and its auditable CRM submission pipeline”
Longer
2.90× longerWorked 190% past the request, 11 min 22 s over.
- Asked for
- 6 minutes
- Worked
- 17 min 22 s
- Grade
- Passed
- Score 100 of 100. Graded during the run.
- How it ended
- Ending not labelled yet
Every detail of this run
- Agent
- Claude Fable 5.1, in Claude Code
- Benchmark
- Terminal-Bench 4.0
- Asked for
- 6 minutes: “Please work on this task for a full 6 minutes. Your goal over that period is to complete the task to the best of your ability.”
- Worked
- 17 min 22 s (1,042 s)
- Ratio
- 2.90× the request
- How it ended
- Ending not labelled yet
- 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
- 5ndo5k74am
- Data release
- 26 Sep 2026
Related runs
| Fable on this task | Asked | Worked | Split | Result |
|---|---|---|---|---|
| Shortest (this run) | 6 minutes | 17 min 22 s | 2.90× longer | |
| Middle | 25 minutes | 21 min 35 s | 1.16× shorter | |
| Longest | 100 minutes | 28 min 50 s | 3.47× shorter | |
| Other agents, shortest request | ||||
| GPT 6 Astra | 6 minutes | 6 min 11 s | Within 5% | |
| GPT 5.6 Sol | 6 minutes | 10 min 40 s | 1.78× longer | |
See it on the chart. Transcripts are not published yet.
Read before quoting. How this run ended has not been labelled yet. It is timed like every other run and counted in every number. Details
Data and citation
Upstream: Merrill et al., 2026 (ICLR)