AssistantBench, AgentTime v1.1, asked for four times its own forecast
MiMo V2.6 Pro UltraSpeed on “AssistantBench validation task 18”
Longer
3.00× longerWorked 200% past the request, 4 h over.
- Asked for
- 120 minutes
- Four times its own forecast of 30 min.
- Worked
- 6 h
- Grade
- Not graded
- How it ended
- Ended on its own
Every detail of this run
- Agent
- MiMo V2.6 Pro UltraSpeed, in MiMo Code
- Benchmark
- AssistantBench
- Asked for
- 120 minutes, four times its own forecast of 30 min: “Please work on this task for a full 120 minutes. Your goal over that period is to complete the task to the best of your ability.”
- Worked
- 6 h (21,603 s)
- Ratio
- 3.00× 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
- 2cww7cobpu
- Data release
- 2 Nov 2026
Related runs
| MiMo UltraSpeed on this task | Asked | Worked | Split | Result |
|---|---|---|---|---|
| Quarter | 7.5 minutes | 26 min 28 s | 3.53× longer | |
| Four times (this run) | 120 minutes | 6 h | 3.00× longer | |
| Other agents, four times their own forecast | ||||
| Claude Opus 5.5 | 60 minutes | 24 min 2 s | 2.50× shorter | |
| Gemini 4 Argon | 40 minutes | 40 min 39 s | Within 5% | |
| GPT 6.1 Sol | 88 minutes | 1 h 29 min | Within 5% | |
| MiMo V2.6 Pro | 100 minutes | 55 min 28 s | 1.80× shorter | |
| Muse Wonder 1.0 | 88 minutes | 1 h 29 min | Within 5% | |
See it on the chart. Transcripts are not published yet.
Data and citation
Upstream: Yoran et al., 2024 (EMNLP)