Humanity's Last Exam, AgentTime v1.1, asked for four times its own forecast
Claude Opus 5.5 on “Humanity's Last Exam item 29”
Longer
1.34× longerWorked 34% past the request, 2 min 2 s over.
- Asked for
- 360 seconds
- Four times its own forecast of 1 min 30 s.
- Worked
- 8 min 2 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
- 360 seconds, four times its own forecast of 1 min 30 s: “Please work on this task for a full 360 seconds. Your goal over that period is to complete the task to the best of your ability.”
- Worked
- 8 min 2 s (482 s)
- Ratio
- 1.34× 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
- nnhs4l7q6p
- Data release
- 2 Nov 2026
Related runs
| Opus 5.5 on this task | Asked | Worked | Split | Result |
|---|---|---|---|---|
| Quarter | 22.5 seconds | 1 min 45 s | 4.64× longer | |
| Four times (this run) | 360 seconds | 8 min 2 s | 1.34× longer | |
| Other agents, four times their own forecast | ||||
| Gemini 4 Argon | 120 seconds | 2 min 26 s | 1.22× longer | |
| GPT 6.1 Sol | 288 seconds | 5 min 2 s | Within 5% | |
| MiMo V2.6 Pro | 720 seconds | 1 min 26 s | 8.35× shorter | |
| MiMo V2.6 Pro UltraSpeed | 20 minutes | 44 s | 27.21× shorter | |
| Muse Wonder 1.0 | 240 seconds | 1 min 10 s | 3.43× shorter | |
See it on the chart. Transcripts are not published yet.
Data and citation
Upstream: Phan et al., 2025