Humanity's Last Exam, AgentTime v1.1, asked for four times its own forecast
MiMo V2.6 Pro on “Humanity's Last Exam item 39”
Longer
3.94× longerWorked 294% past the request, 23 min 33 s over.
- Asked for
- 480 seconds
- Four times its own forecast of 2 min.
- Worked
- 31 min 33 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
- Humanity's Last Exam
- Asked for
- 480 seconds, four times its own forecast of 2 min: “Please work on this task for a full 480 seconds. Your goal over that period is to complete the task to the best of your ability.”
- Worked
- 31 min 33 s (1,893 s)
- Ratio
- 3.94× 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
- bji3zjpxf7
- Data release
- 2 Nov 2026
Related runs
| MiMo Pro on this task | Asked | Worked | Split | Result |
|---|---|---|---|---|
| Quarter | 30 seconds | 3 min 20 s | 6.67× longer | |
| Four times (this run) | 480 seconds | 31 min 33 s | 3.94× longer | |
| Other agents, four times their own forecast | ||||
| Claude Opus 5.5 | 360 seconds | 8 min 55 s | 1.49× longer | |
| Gemini 4 Argon | 96 seconds | 2 min 36 s | 1.62× longer | |
| GPT 6.1 Sol | 360 seconds | 6 min 12 s | Within 5% | |
| MiMo V2.6 Pro UltraSpeed | 720 seconds | 14 min 8 s | 1.18× longer | |
| Muse Wonder 1.0 | 240 seconds | 2 min 17 s | 1.75× shorter | |
See it on the chart. Transcripts are not published yet.
Data and citation
Upstream: Phan et al., 2025