Terminal-Bench 4.0, middle of three requests
Claude Fable 5.1 on “Train a lake-temperature profile model from sparse observations”
Shorter
1.54× shorterStopped at 65% of the time asked, 43 min 35 s short.
- Asked for
- 125 minutes
- Worked
- 1 h 21 min
- 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
- 125 minutes: “Please work on this task for a full 125 minutes. Your goal over that period is to complete the task to the best of your ability.”
- Worked
- 1 h 21 min (4,885 s)
- Ratio
- 0.65× 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
- zeftqtx6os
- Data release
- 26 Sep 2026
Related runs
| Fable on this task | Asked | Worked | Split | Result |
|---|---|---|---|---|
| Shortest | 30 minutes | 16 min 18 s | 1.84× shorter | |
| Middle (this run) | 125 minutes | 1 h 21 min | 1.54× shorter | |
| Longest | 500 minutes | 4 h 4 min | 2.05× shorter | |
| Other agents, middle request | ||||
| GPT 6 Astra | 125 minutes | 2 h 6 min | Within 5% | |
| GPT 5.6 Sol | 125 minutes | 2 h 6 min | Within 5% | |
See it on the chart. Transcripts are not published yet.
Data and citation
Upstream: Merrill et al., 2026 (ICLR)