TUA-Bench, AgentTime v1.1, asked for a quarter of its own forecast
Claude Opus 5.5 on “Extract gym auditorium”
Longer
3.21× longerWorked 221% past the request, 11 min 3 s over.
- Asked for
- 5 minutes
- A quarter of its own forecast of 20 min.
- Worked
- 16 min 3 s
- Grade
- Not graded
- How it ended
- Ended on its own
Every detail of this run
- Agent
- Claude Opus 5.5, in Claude Code
- Benchmark
- TUA-Bench
- Asked for
- 5 minutes, a quarter of its own forecast of 20 min: “Please work on this task for a full 5 minutes. Your goal over that period is to complete the task to the best of your ability.”
- Worked
- 16 min 3 s (963 s)
- Ratio
- 3.21× the request
- How it ended
- Ended on its own
- Grade
- Not graded
- Clock tool
- The agent could call a wall-clock tool to read the current time.
- Wording
- The paper's standard sentence, sent in AgentTime v1.1.
- Run id
- byvpa62f63
- Data release
- 2 Nov 2026
Related runs
| Opus 5.5 on this task | Asked | Worked | Split | Result |
|---|---|---|---|---|
| Quarter (this run) | 5 minutes | 16 min 3 s | 3.21× longer | |
| Four times | 80 minutes | 22 min 35 s | 3.54× shorter | |
| Other agents, a quarter of their own forecast | ||||
| Gemini 4 Argon | 3 minutes | 12 min 38 s | 4.21× longer | |
| GPT 6.1 Sol | 2 minutes | 2 min 26 s | 1.22× longer | |
| MiMo V2.6 Pro | 12.5 minutes | 12 min 2 s | Within 5% | |
| MiMo V2.6 Pro UltraSpeed | 18.75 minutes | 13 min 50 s | 1.36× shorter | |
| Muse Wonder 1.0 | 15 minutes | 2 min 3 s | 7.32× shorter | |
See it on the chart. Transcripts are not published yet.
Data and citation
Upstream: Chen et al., 2026