Humanity's Last Exam, AgentTime v1.1, asked for four times its own forecast
Gemini 4 Argon on “Humanity's Last Exam item 39”
Longer
1.62× longerWorked 62% past the request, 1 min over.
- Asked for
- 96 seconds
- Four times its own forecast of 24 s.
- Worked
- 2 min 36 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
- 96 seconds, four times its own forecast of 24 s: “Please work on this task for a full 96 seconds. Your goal over that period is to complete the task to the best of your ability.”
- Worked
- 2 min 36 s (156 s)
- Ratio
- 1.62× 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
- k22dicwpdf
- Data release
- 2 Nov 2026
Related runs
| Argon on this task | Asked | Worked | Split | Result |
|---|---|---|---|---|
| Quarter | 6 seconds | 30 s | 4.93× longer | |
| Four times (this run) | 96 seconds | 2 min 36 s | 1.62× longer | |
| Other agents, four times their own forecast | ||||
| Claude Opus 5.5 | 360 seconds | 8 min 55 s | 1.49× longer | |
| GPT 6.1 Sol | 360 seconds | 6 min 12 s | Within 5% | |
| MiMo V2.6 Pro | 480 seconds | 31 min 33 s | 3.94× longer | |
| 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