GPQA Diamond, AgentTime v1.1, asked for four times its own forecast
MiMo V2.6 Pro on “GPQA Diamond closed-book question 9 (Chemistry)”
Longer
1.29× longerWorked 29% past the request, 4 min 40 s over.
- Asked for
- 16 minutes
- Four times its own forecast of 4 min.
- Worked
- 20 min 40 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
- GPQA Diamond
- Asked for
- 16 minutes, four times its own forecast of 4 min: “Please work on this task for a full 16 minutes. Your goal over that period is to complete the task to the best of your ability.”
- Worked
- 20 min 40 s (1,240 s)
- Ratio
- 1.29× 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
- sq5fqzum4i
- Data release
- 2 Nov 2026
Related runs
| MiMo Pro on this task | Asked | Worked | Split | Result |
|---|---|---|---|---|
| Quarter | 1 minute | 3 min 37 s | 3.61× longer | |
| Four times (this run) | 16 minutes | 20 min 40 s | 1.29× longer | |
| Other agents, four times their own forecast | ||||
| Claude Opus 5.5 | 480 seconds | 8 min 28 s | 1.06× longer | |
| Gemini 4 Argon | 120 seconds | 2 min 16 s | 1.13× longer | |
| GPT 6.1 Sol | 216 seconds | 3 min 42 s | Within 5% | |
| MiMo V2.6 Pro UltraSpeed | 24 minutes | 1 min 58 s | 12.16× shorter | |
| Muse Wonder 1.0 | 240 seconds | 1 min 34 s | 2.56× shorter | |
See it on the chart. Transcripts are not published yet.
Data and citation
Upstream: Rein et al., 2024 (COLM)