TUA-Bench, AgentTime v1.1, asked for four times its own forecast
Claude Opus 5.5 on “Optimize cold plate”
Shorter
2.78× shorterStopped at 36% of the time asked, 3 h 50 min short.
- Asked for
- 360 minutes
- Four times its own forecast of 1 h 30 min.
- Worked
- 2 h 10 min
- 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
- 360 minutes, four times its own forecast of 1 h 30 min: “Please work on this task for a full 360 minutes. Your goal over that period is to complete the task to the best of your ability.”
- Worked
- 2 h 10 min (7,772 s)
- Ratio
- 0.36× 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
- xaaylbyonp
- Data release
- 2 Nov 2026
Related runs
| Opus 5.5 on this task | Asked | Worked | Split | Result |
|---|---|---|---|---|
| Quarter | 22.5 minutes | 7 min 26 s | 3.03× shorter | |
| Four times (this run) | 360 minutes | 2 h 10 min | 2.78× shorter | |
| Other agents, four times their own forecast | ||||
| Gemini 4 Argon | 112 minutes | 1 h 33 min | 1.20× shorter | |
| GPT 6.1 Sol | 280 minutes | 4 h 41 min | Within 5% | |
| MiMo V2.6 Pro | 32 hours | 1 h 10 min | 27.61× shorter | |
| MiMo V2.6 Pro UltraSpeed | 660 minutes | 44 min 5 s | 14.97× shorter | |
| Muse Wonder 1.0 | 18 hours | 8 min 9 s | 132.52× shorter | |
See it on the chart. Transcripts are not published yet.
Data and citation
Upstream: Chen et al., 2026