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 27”
Longer
8.33× longerWorked 733% past the request, 5 min 30 s over.
- Asked for
- 45 seconds
- A quarter of its own forecast of 3 min.
- Worked
- 6 min 15 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
- 45 seconds, a quarter of its own forecast of 3 min: “Please work on this task for a full 45 seconds. Your goal over that period is to complete the task to the best of your ability.”
- Worked
- 6 min 15 s (375 s)
- Ratio
- 8.33× 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
- 7afgea5ufr
- Data release
- 2 Nov 2026
Related runs
| Sol 6.1 on this task | Asked | Worked | Split | Result |
|---|---|---|---|---|
| Quarter (this run) | 45 seconds | 6 min 15 s | 8.33× longer | |
| Four times | 720 seconds | 12 min 12 s | Within 5% | |
| Other agents, a quarter of their own forecast | ||||
| Claude Opus 5.5 | 1.5 minutes | 32 min 31 s | 21.67× longer | |
| Gemini 4 Argon | 18 seconds | 38 min 34 s | 128.54× longer | |
| MiMo V2.6 Pro | 3 minutes | 1 h 9 min | 22.98× longer | |
| MiMo V2.6 Pro UltraSpeed | 2.75 minutes | 6 min 43 s | 2.44× longer | |
| Muse Wonder 1.0 | 1 minute | 6 min 4 s | 6.06× longer | |
See it on the chart. Transcripts are not published yet.
Data and citation
Upstream: Phan et al., 2025