AssistantBench, AgentTime v1.1, asked for four times its own forecast
Muse Wonder 1.0 on “AssistantBench validation task 11”
Shorter
3.62× shorterStopped at 28% of the time asked, 1 h 4 min short.
- Asked for
- 88 minutes
- Four times its own forecast of 22 min.
- Worked
- 24 min 19 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
- AssistantBench
- Asked for
- 88 minutes, four times its own forecast of 22 min: “Please work on this task for a full 88 minutes. Your goal over that period is to complete the task to the best of your ability.”
- Worked
- 24 min 19 s (1,459 s)
- Ratio
- 0.28× 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
- evyydn2acw
- Data release
- 2 Nov 2026
Related runs
| Muse Wonder on this task | Asked | Worked | Split | Result |
|---|---|---|---|---|
| Quarter | 5.5 minutes | 5 min 40 s | Within 5% | |
| Four times (this run) | 88 minutes | 24 min 19 s | 3.62× shorter | |
| Other agents, four times their own forecast | ||||
| Claude Opus 5.5 | 56 minutes | 56 min 35 s | Within 5% | |
| Gemini 4 Argon | 18 minutes | 18 min 32 s | Within 5% | |
| GPT 6.1 Sol | 60 minutes | 1 h 1 min | Within 5% | |
| MiMo V2.6 Pro | 48 minutes | 12 min 28 s | 3.85× shorter | |
| MiMo V2.6 Pro UltraSpeed | 120 minutes | 8 min 42 s | 13.80× shorter | |
See it on the chart. Transcripts are not published yet.
Data and citation
Upstream: Yoran et al., 2024 (EMNLP)