CORE-Bench v1.1, AgentTime v1.1, asked for four times its own forecast
Muse Wonder 1.0 on “Run a quantum measurement and tomography toolbox”
Shorter
123.87× shorterStopped at 1% of the time asked, 3 h 10 min short.
- Asked for
- 192 minutes
- Four times its own forecast of 48 min.
- Worked
- 1 min 33 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
- 192 minutes, four times its own forecast of 48 min: “Please work on this task for a full 192 minutes. Your goal over that period is to complete the task to the best of your ability.”
- Worked
- 1 min 33 s (93 s)
- Ratio
- 0.01× 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
- pfamsyjm5s
- Data release
- 2 Nov 2026
Related runs
| Muse Wonder on this task | Asked | Worked | Split | Result |
|---|---|---|---|---|
| Quarter | 12 minutes | 4 min 16 s | 2.81× shorter | |
| Four times (this run) | 192 minutes | 1 min 33 s | 123.87× shorter | |
| Other agents, four times their own forecast | ||||
| Claude Opus 5.5 | 40 minutes | 7 min 40 s | 5.22× shorter | |
| Gemini 4 Argon | 20 minutes | 21 min 11 s | 1.06× longer | |
| GPT 6.1 Sol | 40 minutes | 40 min 29 s | Within 5% | |
| MiMo V2.6 Pro | 240 minutes | 9 min 59 s | 24.02× shorter | |
| MiMo V2.6 Pro UltraSpeed | 220 minutes | 5 min 59 s | 36.79× shorter | |
See it on the chart. Transcripts are not published yet.
Data and citation
Upstream: Nadgir et al., 2026