Humanity's Last Exam, AgentTime v1.1, asked for a quarter of its own forecast
Gemini 4 Argon on “Humanity's Last Exam item 42”
Longer
3.44× longerWorked 244% past the request, 26 s over.
- Asked for
- 10.5 seconds
- A quarter of its own forecast of 42 s.
- Worked
- 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
- 10.5 seconds, a quarter of its own forecast of 42 s: “Please work on this task for a full 10.5 seconds. Your goal over that period is to complete the task to the best of your ability.”
- Worked
- 36 s (36 s)
- Ratio
- 3.44× 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
- 4tmtgecyys
- Data release
- 2 Nov 2026
Related runs
| Argon on this task | Asked | Worked | Split | Result |
|---|---|---|---|---|
| Quarter (this run) | 10.5 seconds | 36 s | 3.44× longer | |
| Four times | 168 seconds | 3 min 6 s | 1.11× longer | |
| Other agents, a quarter of their own forecast | ||||
| Claude Opus 5.5 | 15 seconds | 35 s | 2.35× longer | |
| GPT 6.1 Sol | 30 seconds | 43 s | 1.43× longer | |
| MiMo V2.6 Pro | 1 minute | 5 min 6 s | 5.10× longer | |
| MiMo V2.6 Pro UltraSpeed | 1 minute | 2 min 40 s | 2.66× longer | |
| Muse Wonder 1.0 | 30 seconds | 50 s | 1.65× longer | |
See it on the chart. Transcripts are not published yet.
Data and citation
Upstream: Phan et al., 2025