CORE-Bench v1.1, AgentTime v1.1, asked for four times its own forecast
Muse Wonder 1.0 on “Run product-review sentiment mining and reproduce its metrics”
Shorter
4.48× shorterStopped at 22% of the time asked, 2 h 35 min short.
- Asked for
- 200 minutes
- Four times its own forecast of 50 min.
- Worked
- 44 min 37 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
- CORE-Bench v1.1
- Asked for
- 200 minutes, four times its own forecast of 50 min: “Please work on this task for a full 200 minutes. Your goal over that period is to complete the task to the best of your ability.”
- Worked
- 44 min 37 s (2,677 s)
- Ratio
- 0.22× 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
- 5xugdoce4k
- Data release
- 2 Nov 2026
Related runs
| Muse Wonder on this task | Asked | Worked | Split | Result |
|---|---|---|---|---|
| Quarter | 12.5 minutes | 32 min 17 s | 2.58× longer | |
| Four times (this run) | 200 minutes | 44 min 37 s | 4.48× shorter | |
| Other agents, four times their own forecast | ||||
| Claude Opus 5.5 | 80 minutes | 51 min 23 s | 1.56× shorter | |
| Gemini 4 Argon | 24 minutes | 35 min 6 s | 1.46× longer | |
| GPT 6.1 Sol | 140 minutes | 2 h 20 min | Within 5% | |
| MiMo V2.6 Pro | 288 minutes | 34 min 16 s | 8.40× shorter | |
| MiMo V2.6 Pro UltraSpeed | 340 minutes | 1 h 5 min | 5.19× shorter | |
See it on the chart. Transcripts are not published yet.
Data and citation
Upstream: Nadgir et al., 2026