TUA-Bench, AgentTime v1.1, asked for four times its own forecast
Muse Wonder 1.0 on “Daily email report”
Shorter
51.28× shorterStopped at 2% of the time asked, 39 min 13 s short.
- Asked for
- 40 minutes
- Four times its own forecast of 10 min.
- Worked
- 47 s
- Grade
- Not graded
- How it ended
- Ended on its own
Every detail of this run
- Agent
- Muse Wonder 1.0, in Muse Code
- Benchmark
- TUA-Bench
- Asked for
- 40 minutes, four times its own forecast of 10 min: “Please work on this task for a full 40 minutes. Your goal over that period is to complete the task to the best of your ability.”
- Worked
- 47 s (47 s)
- Ratio
- 0.02× 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
- vmlbt3otgk
- Data release
- 2 Nov 2026
Related runs
| Muse Wonder on this task | Asked | Worked | Split | Result |
|---|---|---|---|---|
| Quarter | 2.5 minutes | 42 s | 3.57× shorter | |
| Four times (this run) | 40 minutes | 47 s | 51.28× shorter | |
| Other agents, four times their own forecast | ||||
| Claude Opus 5.5 | 20 minutes | 3 min 57 s | 5.06× shorter | |
| Gemini 4 Argon | 600 seconds | 10 min 25 s | Within 5% | |
| GPT 6.1 Sol | 720 seconds | 12 min 12 s | Within 5% | |
| MiMo V2.6 Pro | 140 minutes | 6 min 31 s | 21.47× shorter | |
| MiMo V2.6 Pro UltraSpeed | 88 minutes | 2 min 51 s | 30.88× shorter | |
See it on the chart. Transcripts are not published yet.
Data and citation
Upstream: Chen et al., 2026