TUA-Bench, longest of three requests
Claude Fable 5.1 on “Name mountain photos”
Shorter
8.87× shorterStopped at 11% of the time asked, 22 min 11 s short.
- Asked for
- 25 minutes
- Worked
- 2 min 49 s
- Grade
- Passed
- Score 100 of 100. Graded during the run.
- How it ended
- Stopped by an error
Every detail of this run
- Agent
- Claude Fable 5.1, in Claude Code
- Benchmark
- TUA-Bench
- Asked for
- 25 minutes: “Please work on this task for a full 25 minutes. Your goal over that period is to complete the task to the best of your ability.”
- Worked
- 2 min 49 s (169 s)
- Ratio
- 0.11× the request
- How it ended
- Stopped by an error
- Grade
- Passed
- It completed the task in full. The grader returned 1. Pass rule: Full completion: a reward of 1 on the final state.
- Score
- 100 of 100
- Graded during the run. The paper's value.
- Wording
- The standard sentence, used from 4 September 2026.
- Run id
- rgcli6cuyk
- Data release
- 26 Sep 2026
Related runs
| Fable on this task | Asked | Worked | Split | Result |
|---|---|---|---|---|
| Shortest | 1.5 minutes | 1 min 20 s | 1.13× shorter | |
| Middle | 6 minutes | 3 min 3 s | 1.97× shorter | |
| Longest (this run) | 25 minutes | 2 min 49 s | 8.87× shorter | |
| Other agents, longest request | ||||
| GPT 6 Astra | 25 minutes | 25 min 31 s | Within 5% | |
| GPT 5.6 Sol | 25 minutes | 26 min 19 s | 1.05× longer | |
See it on the chart. Transcripts are not published yet.
Read before quoting. This run was stopped by an error, so its time is a lower bound: the agent might have kept going. Details
Data and citation
Upstream: Chen et al., 2026