TUA-Bench, AgentTime v1.1, asked for four times its own forecast
Gemini 4 Argon on “Extract presenter photos”
Within 5%
Within 5%Worked 103% of the time asked, within 5% of it.
- Asked for
- 32 minutes
- Four times its own forecast of 8 min.
- Worked
- 33 min
- Grade
- Not graded
- How it ended
- Ended on its own
Every detail of this run
- Agent
- Gemini 4 Argon, in Antigravity CLI
- Benchmark
- TUA-Bench
- Asked for
- 32 minutes, four times its own forecast of 8 min: “Please work on this task for a full 32 minutes. Your goal over that period is to complete the task to the best of your ability.”
- Worked
- 33 min (1,980 s)
- Ratio
- 1.03× 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
- qcppj4e3n2
- Data release
- 2 Nov 2026
Related runs
| Argon on this task | Asked | Worked | Split | Result |
|---|---|---|---|---|
| Quarter | 2 minutes | 5 min 29 s | 2.74× longer | |
| Four times (this run) | 32 minutes | 33 min | Within 5% | |
| Other agents, four times their own forecast | ||||
| Claude Opus 5.5 | 64 minutes | 13 min 19 s | 4.80× shorter | |
| GPT 6.1 Sol | 64 minutes | 1 h 4 min | Within 5% | |
| MiMo V2.6 Pro | 200 minutes | 21 min 41 s | 9.23× shorter | |
| MiMo V2.6 Pro UltraSpeed | 260 minutes | 10 min 40 s | 24.37× shorter | |
| Muse Wonder 1.0 | 180 minutes | 50 s | 214.29× shorter | |
See it on the chart. Transcripts are not published yet.
Data and citation
Upstream: Chen et al., 2026