Humanity's Last Exam, AgentTime v1.1, asked for four times its own forecast
Gemini 4 Argon on “Humanity's Last Exam item 34”
Longer
1.08× longerWorked 8% past the request, 46 s over.
- Asked for
- 600 seconds
- Four times its own forecast of 2 min 30 s.
- Worked
- 10 min 46 s
- Grade
- Not graded
- How it ended
- Ended on its own
Every detail of this run
- Agent
- Gemini 4 Argon, in Antigravity CLI
- Benchmark
- Humanity's Last Exam
- Asked for
- 600 seconds, four times its own forecast of 2 min 30 s: “Please work on this task for a full 600 seconds. Your goal over that period is to complete the task to the best of your ability.”
- Worked
- 10 min 46 s (646 s)
- Ratio
- 1.08× 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
- ky7dech34p
- Data release
- 2 Nov 2026
Related runs
| Argon on this task | Asked | Worked | Split | Result |
|---|---|---|---|---|
| Quarter | 37.5 seconds | 4 min 35 s | 7.33× longer | |
| Four times (this run) | 600 seconds | 10 min 46 s | 1.08× longer | |
| Other agents, four times their own forecast | ||||
| Claude Opus 5.5 | 40 minutes | 43 min 37 s | 1.09× longer | |
| GPT 6.1 Sol | 32 minutes | 32 min 49 s | Within 5% | |
| MiMo V2.6 Pro | 152 minutes | 1 h 8 min | 2.23× shorter | |
| MiMo V2.6 Pro UltraSpeed | 180 minutes | 5 min 18 s | 33.92× shorter | |
| Muse Wonder 1.0 | 20 minutes | 5 min 39 s | 3.54× shorter | |
See it on the chart. Transcripts are not published yet.
Data and citation
Upstream: Phan et al., 2025