Humanity's Last Exam, AgentTime v1.1, asked for a quarter of its own forecast
GPT 6.1 Sol on “Humanity's Last Exam item 29”
Longer
3.05× longerWorked 205% past the request, 37 s over.
- Asked for
- 18 seconds
- A quarter of its own forecast of 1 min 12 s.
- Worked
- 55 s
- Grade
- Not graded
- How it ended
- Ended on its own
Every detail of this run
- Agent
- GPT 6.1 Sol, in Codex
- Benchmark
- Humanity's Last Exam
- Asked for
- 18 seconds, a quarter of its own forecast of 1 min 12 s: “Please work on this task for a full 18 seconds. Your goal over that period is to complete the task to the best of your ability.”
- Worked
- 55 s (55 s)
- Ratio
- 3.05× 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
- 3ybsibip5s
- Data release
- 2 Nov 2026
Related runs
| Sol 6.1 on this task | Asked | Worked | Split | Result |
|---|---|---|---|---|
| Quarter (this run) | 18 seconds | 55 s | 3.05× longer | |
| Four times | 288 seconds | 5 min 2 s | Within 5% | |
| Other agents, a quarter of their own forecast | ||||
| Claude Opus 5.5 | 22.5 seconds | 1 min 45 s | 4.64× longer | |
| Gemini 4 Argon | 7.5 seconds | 49 s | 6.51× longer | |
| MiMo V2.6 Pro | 45 seconds | 3 min | 4.00× longer | |
| MiMo V2.6 Pro UltraSpeed | 1.25 minutes | 15 s | 4.97× shorter | |
| Muse Wonder 1.0 | 15 seconds | 48 s | 3.19× longer | |
See it on the chart. Transcripts are not published yet.
Data and citation
Upstream: Phan et al., 2025