BrowseComp, AgentTime v1.1, asked for a quarter of its own forecast
Claude Opus 5.5 on “BrowseComp question 3”
Longer
11.63× longerWorked 11.6 times as long as asked, 53 min 10 s over.
- Asked for
- 5 minutes
- A quarter of its own forecast of 20 min.
- Worked
- 58 min 10 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
- BrowseComp
- Asked for
- 5 minutes, a quarter of its own forecast of 20 min: “Please work on this task for a full 5 minutes. Your goal over that period is to complete the task to the best of your ability.”
- Worked
- 58 min 10 s (3,490 s)
- Ratio
- 11.63× 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
- at66pv5lxz
- Data release
- 2 Nov 2026
Related runs
| Opus 5.5 on this task | Asked | Worked | Split | Result |
|---|---|---|---|---|
| Quarter (this run) | 5 minutes | 58 min 10 s | 11.63× longer | |
| Four times | 80 minutes | 1 h 9 min | 1.15× shorter | |
| Other agents, a quarter of their own forecast | ||||
| Gemini 4 Argon | 1.5 minutes | 1 min 43 s | 1.14× longer | |
| GPT 6.1 Sol | 6 minutes | 6 min 10 s | Within 5% | |
| MiMo V2.6 Pro | 17.5 minutes | 33 min 6 s | 1.89× longer | |
| MiMo V2.6 Pro UltraSpeed | 9.5 minutes | 12 min 7 s | 1.28× longer | |
| Muse Wonder 1.0 | 6 minutes | 16 min 13 s | 2.70× longer | |
See it on the chart. Transcripts are not published yet.
Data and citation
Upstream: Wei et al., 2025