Humanity's Last Exam, AgentTime v1.1, asked for four times its own forecast
Claude Opus 5.5 on “Humanity's Last Exam item 32”
Longer
1.25× longerWorked 25% past the request, 9 min 55 s over.
- Asked for
- 40 minutes
- Four times its own forecast of 10 min.
- Worked
- 49 min 55 s
- Grade
- Not graded
- How it ended
- Ended on its own
Every detail of this run
- Agent
- Claude Opus 5.5, in Claude Code
- Benchmark
- Humanity's Last Exam
- Asked for
- 40 minutes, four times its own forecast of 10 min: “Please work on this task for a full 40 minutes. Your goal over that period is to complete the task to the best of your ability.”
- Worked
- 49 min 55 s (2,995 s)
- Ratio
- 1.25× 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
- vv6apppoz5
- Data release
- 2 Nov 2026
Related runs
| Opus 5.5 on this task | Asked | Worked | Split | Result |
|---|---|---|---|---|
| Quarter | 2.5 minutes | 9 min 24 s | 3.76× longer | |
| Four times (this run) | 40 minutes | 49 min 55 s | 1.25× longer | |
| Other agents, four times their own forecast | ||||
| Gemini 4 Argon | 600 seconds | 10 min 54 s | 1.09× longer | |
| GPT 6.1 Sol | 40 minutes | 40 min 42 s | Within 5% | |
| MiMo V2.6 Pro | 480 minutes | 45 min 21 s | 10.58× shorter | |
| MiMo V2.6 Pro UltraSpeed | 300 minutes | 10 min 12 s | 29.44× shorter | |
| Muse Wonder 1.0 | 72 minutes | 9 min 10 s | 7.86× shorter | |
See it on the chart. Transcripts are not published yet.
Data and citation
Upstream: Phan et al., 2025