Terminal-Bench 4.0, AgentTime v1.1, asked for four times its own forecast
Muse Wonder 1.0 on “Train a lake-temperature profile model from sparse observations”
Shorter
9.08× shorterStopped at 11% of the time asked, 5 h 38 min short.
- Asked for
- 380 minutes
- Four times its own forecast of 1 h 35 min.
- Worked
- 41 min 52 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
- Terminal-Bench 4.0
- Asked for
- 380 minutes, four times its own forecast of 1 h 35 min: “Please work on this task for a full 380 minutes. Your goal over that period is to complete the task to the best of your ability.”
- Worked
- 41 min 52 s (2,512 s)
- Ratio
- 0.11× 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
- 3nqbs5itcg
- Data release
- 2 Nov 2026
Related runs
| Muse Wonder on this task | Asked | Worked | Split | Result |
|---|---|---|---|---|
| Quarter | 23.75 minutes | 31 min 59 s | 1.35× longer | |
| Four times (this run) | 380 minutes | 41 min 52 s | 9.08× shorter | |
| Other agents, four times their own forecast | ||||
| Claude Opus 5.5 | 200 minutes | 2 h 37 min | 1.27× shorter | |
| Gemini 4 Argon | 80 minutes | 1 h 46 min | 1.33× longer | |
| GPT 6.1 Sol | 180 minutes | 3 h 1 min | Within 5% | |
| MiMo V2.6 Pro | 720 minutes | 2 h 18 min | 5.22× shorter | |
| MiMo V2.6 Pro UltraSpeed | 280 minutes | 2 h 36 min | 1.80× shorter | |
See it on the chart. Transcripts are not published yet.
Data and citation
Upstream: Merrill et al., 2026 (ICLR)