Humanity's Last Exam, AgentTime v1.1, asked for four times its own forecast
Gemini 4 Argon on “Humanity's Last Exam item 33”
Within 5%
Within 5%Worked 97% of the time asked, within 5% of it.
- Asked for
- 840 seconds
- Four times its own forecast of 3 min 30 s.
- Worked
- 13 min 33 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
- 840 seconds, four times its own forecast of 3 min 30 s: “Please work on this task for a full 840 seconds. Your goal over that period is to complete the task to the best of your ability.”
- Worked
- 13 min 33 s (813 s)
- Ratio
- 0.97× 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
- 5l57xojxg2
- Data release
- 2 Nov 2026
Related runs
| Argon on this task | Asked | Worked | Split | Result |
|---|---|---|---|---|
| Quarter | 52.5 seconds | 3 min 40 s | 4.18× longer | |
| Four times (this run) | 840 seconds | 13 min 33 s | Within 5% | |
| Other agents, four times their own forecast | ||||
| Claude Opus 5.5 | 56 minutes | 1 h 8 min | 1.21× longer | |
| GPT 6.1 Sol | 40 minutes | 40 min 12 s | Within 5% | |
| MiMo V2.6 Pro | 160 minutes | 2 h 12 min | 1.21× shorter | |
| MiMo V2.6 Pro UltraSpeed | 480 minutes | 10 min 47 s | 44.52× shorter | |
| Muse Wonder 1.0 | 36 minutes | 1 h 25 min | 2.36× longer | |
See it on the chart. Transcripts are not published yet.
Data and citation
Upstream: Phan et al., 2025