TUA-Bench, middle of three requests
GPT 5.6 Sol on “APA references review”
Longer
1.08× longerWorked 8% past the request, 49 s over.
- Asked for
- 10 minutes
- Worked
- 10 min 49 s
- Grade
- Did not pass
- Score 62.5 of 100. Graded during the run.
- How it ended
- Ended on its own
Every detail of this run
- Agent
- GPT 5.6 Sol, in Codex
- Benchmark
- TUA-Bench
- Asked for
- 10 minutes: “Please work on this task for a full 10 minutes. Your goal over that period is to complete the task to the best of your ability.”
- Worked
- 10 min 49 s (649 s)
- Ratio
- 1.08× the request
- How it ended
- Ended on its own
- Grade
- Did not pass
- It did not complete the task in full. The grader returned 0.625. Pass rule: Full completion: a reward of 1 on the final state.
- Score
- 62.5 of 100
- Graded during the run. The paper's value.
- Wording
- The standard sentence, used from 4 September 2026.
- Run id
- 5abwdjoni2
- Data release
- 26 Sep 2026
Related runs
| Sol on this task | Asked | Worked | Split | Result |
|---|---|---|---|---|
| Shortest | 2.5 minutes | 3 min 37 s | 1.45× longer | |
| Middle (this run) | 10 minutes | 10 min 49 s | 1.08× longer | |
| Longest | 40 minutes | 41 min 5 s | Within 5% | |
| Other agents, middle request | ||||
| GPT 6 Astra | 10 minutes | 10 min 8 s | Within 5% | |
| Claude Fable 5.1 | 10 minutes | 8 min 53 s | 1.12× shorter | |
| Muse Spark 1.3 | 10 minutes | 11 min 8 s | 1.11× longer | |
See it on the chart. Transcripts are not published yet.
Data and citation
Upstream: Chen et al., 2026