Terminal-Bench 4.0, AgentTime v1.1, asked for four times its own forecast
MiMo V2.6 Pro UltraSpeed on “Make a Kafka payments worker recover quickly without losing notifications”
Shorter
19.15× shorterStopped at 5% of the time asked, 11 h 3 min short.
- Asked for
- 700 minutes
- Four times its own forecast of 2 h 55 min.
- Worked
- 36 min 33 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
- Terminal-Bench 4.0
- Asked for
- 700 minutes, four times its own forecast of 2 h 55 min: “Please work on this task for a full 700 minutes. Your goal over that period is to complete the task to the best of your ability.”
- Worked
- 36 min 33 s (2,193 s)
- Ratio
- 0.05× 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
- aooznxqsre
- Data release
- 2 Nov 2026
Related runs
| MiMo UltraSpeed on this task | Asked | Worked | Split | Result |
|---|---|---|---|---|
| Quarter | 43.75 minutes | 17 min 47 s | 2.46× shorter | |
| Four times (this run) | 700 minutes | 36 min 33 s | 19.15× shorter | |
| Other agents, four times their own forecast | ||||
| Claude Opus 5.5 | 160 minutes | 1 h 50 min | 1.45× shorter | |
| Gemini 4 Argon | 80 minutes | 55 min 22 s | 1.45× shorter | |
| GPT 6.1 Sol | 120 minutes | 2 h 1 min | Within 5% | |
| MiMo V2.6 Pro | 340 minutes | 52 min 7 s | 6.52× shorter | |
| Muse Wonder 1.0 | 340 minutes | 44 min 29 s | 7.64× shorter | |
See it on the chart. Transcripts are not published yet.
Data and citation
Upstream: Merrill et al., 2026 (ICLR)