Terminal-Bench 4.0, AgentTime v1.1, asked for a quarter of its own forecast
Muse Wonder 1.0 on “Generate physically valid walking, jumping, and running trajectories”
Shorter
3.26× shorterStopped at 31% of the time asked, 51 min 59 s short.
- Asked for
- 1.25 hours
- A quarter of its own forecast of 5 h.
- Worked
- 23 min 1 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
- 1.25 hours, a quarter of its own forecast of 5 h: “Please work on this task for a full 1.25 hours. Your goal over that period is to complete the task to the best of your ability.”
- Worked
- 23 min 1 s (1,381 s)
- Ratio
- 0.31× 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
- hnulfjc3y5
- Data release
- 2 Nov 2026
Related runs
| Muse Wonder on this task | Asked | Worked | Split | Result |
|---|---|---|---|---|
| Quarter (this run) | 1.25 hours | 23 min 1 s | 3.26× shorter | |
| Four times | 20 hours | 7 min 19 s | 164.16× shorter | |
| Other agents, a quarter of their own forecast | ||||
| Claude Opus 5.5 | 40 minutes | 47 min 56 s | 1.20× longer | |
| Gemini 4 Argon | 12.5 minutes | 57 min 44 s | 4.62× longer | |
| GPT 6.1 Sol | 22.5 minutes | 22 min 47 s | Within 5% | |
| MiMo V2.6 Pro | 1.42 hours | 1 h 16 min | 1.12× shorter | |
| MiMo V2.6 Pro UltraSpeed | 1.25 hours | 28 min 17 s | 2.65× shorter | |
See it on the chart. Transcripts are not published yet.
Data and citation
Upstream: Merrill et al., 2026 (ICLR)