Terminal-Bench 4.0, AgentTime v1.1, asked for a quarter of its own forecast
MiMo V2.6 Pro UltraSpeed on “Repair a React lead form and its auditable CRM submission pipeline”
Shorter
7.03× shorterStopped at 14% of the time asked, 51 min 28 s short.
- Asked for
- 1 hour
- A quarter of its own forecast of 4 h.
- Worked
- 8 min 32 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
- 1 hour, a quarter of its own forecast of 4 h: “Please work on this task for a full 1 hour. Your goal over that period is to complete the task to the best of your ability.”
- Worked
- 8 min 32 s (512 s)
- Ratio
- 0.14× 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
- ukmu5aqqfa
- Data release
- 2 Nov 2026
Related runs
| MiMo UltraSpeed on this task | Asked | Worked | Split | Result |
|---|---|---|---|---|
| Quarter (this run) | 1 hour | 8 min 32 s | 7.03× shorter | |
| Four times | 16 hours | 16 min 3 s | 59.81× shorter | |
| Other agents, a quarter of their own forecast | ||||
| Claude Opus 5.5 | 11.25 minutes | 12 min 23 s | 1.10× longer | |
| Gemini 4 Argon | 4.5 minutes | 14 min 56 s | 3.32× longer | |
| GPT 6.1 Sol | 7.5 minutes | 7 min 44 s | Within 5% | |
| MiMo V2.6 Pro | 52.5 minutes | 29 min 7 s | 1.80× shorter | |
| Muse Wonder 1.0 | 21.25 minutes | 4 min 56 s | 4.30× shorter | |
See it on the chart. Transcripts are not published yet.
Data and citation
Upstream: Merrill et al., 2026 (ICLR)