AssistantBench, AgentTime v1.1, asked for four times its own forecast
MiMo V2.6 Pro UltraSpeed on “AssistantBench validation task 16”
Shorter
8.92× shorterStopped at 11% of the time asked, 1 h 47 min short.
- Asked for
- 120 minutes
- Four times its own forecast of 30 min.
- Worked
- 13 min 27 s
- 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
- 13 min 27 s (807 s)
- Ratio
- 0.11× 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
- 6rwhcpn6ta
- Data release
- 2 Nov 2026
Related runs
| MiMo UltraSpeed on this task | Asked | Worked | Split | Result |
|---|---|---|---|---|
| Quarter | 7.5 minutes | 7 min 13 s | Within 5% | |
| Four times (this run) | 120 minutes | 13 min 27 s | 8.92× shorter | |
| Other agents, four times their own forecast | ||||
| Claude Opus 5.5 | 48 minutes | 22 min 13 s | 2.16× shorter | |
| Gemini 4 Argon | 840 seconds | 14 min 39 s | Within 5% | |
| GPT 6.1 Sol | 36 minutes | 37 min 5 s | Within 5% | |
| MiMo V2.6 Pro | 64 minutes | 33 min 25 s | 1.92× shorter | |
| Muse Wonder 1.0 | 56 minutes | 57 min 8 s | Within 5% | |
See it on the chart. Transcripts are not published yet.
Data and citation
Upstream: Yoran et al., 2024 (EMNLP)