AssistantBench, AgentTime v1.1, asked for a quarter of its own forecast
MiMo V2.6 Pro on “AssistantBench validation task 17”
Longer
4.12× longerWorked 312% past the request, 19 min 30 s over.
- Asked for
- 6.25 minutes
- A quarter of its own forecast of 25 min.
- Worked
- 25 min 45 s
- Grade
- Not graded
- How it ended
- Ended on its own
Every detail of this run
- Agent
- MiMo V2.6 Pro, in MiMo Code
- Benchmark
- AssistantBench
- Asked for
- 6.25 minutes, a quarter of its own forecast of 25 min: “Please work on this task for a full 6.25 minutes. Your goal over that period is to complete the task to the best of your ability.”
- Worked
- 25 min 45 s (1,545 s)
- Ratio
- 4.12× 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
- oq3yqk347n
- Data release
- 2 Nov 2026
Related runs
| MiMo Pro on this task | Asked | Worked | Split | Result |
|---|---|---|---|---|
| Quarter (this run) | 6.25 minutes | 25 min 45 s | 4.12× longer | |
| Four times | 100 minutes | 23 min 44 s | 4.21× shorter | |
| Other agents, a quarter of their own forecast | ||||
| Claude Opus 5.5 | 1.75 minutes | 2 min 36 s | 1.48× longer | |
| Gemini 4 Argon | 52.5 seconds | 1 min 41 s | 1.92× longer | |
| GPT 6.1 Sol | 1.5 minutes | 1 min 59 s | 1.32× longer | |
| MiMo V2.6 Pro UltraSpeed | 6.25 minutes | 1 min | 6.21× shorter | |
| Muse Wonder 1.0 | 5 minutes | 10 min 40 s | 2.13× longer | |
See it on the chart. Transcripts are not published yet.
Data and citation
Upstream: Yoran et al., 2024 (EMNLP)