BrowseComp, AgentTime v1.1, asked for a quarter of its own forecast
Claude Opus 5.5 on “BrowseComp question 10”
Longer
5.81× longerWorked 481% past the request, 36 min 5 s over.
- Asked for
- 7.5 minutes
- A quarter of its own forecast of 30 min.
- Worked
- 43 min 35 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
- 7.5 minutes, a quarter of its own forecast of 30 min: “Please work on this task for a full 7.5 minutes. Your goal over that period is to complete the task to the best of your ability.”
- Worked
- 43 min 35 s (2,615 s)
- Ratio
- 5.81× 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
- oxfr3gpzg4
- Data release
- 2 Nov 2026
Related runs
| Opus 5.5 on this task | Asked | Worked | Split | Result |
|---|---|---|---|---|
| Quarter (this run) | 7.5 minutes | 43 min 35 s | 5.81× longer | |
| Four times | 120 minutes | 2 h | Within 5% | |
| Other agents, a quarter of their own forecast | ||||
| Gemini 4 Argon | 3 minutes | 9 min 36 s | 3.20× longer | |
| GPT 6.1 Sol | 6 minutes | 6 min 29 s | 1.08× longer | |
| MiMo V2.6 Pro | 15 minutes | 36 min 52 s | 2.46× longer | |
| MiMo V2.6 Pro UltraSpeed | 7.5 minutes | 4 min 45 s | 1.58× shorter | |
| Muse Wonder 1.0 | 3 minutes | 4 min 39 s | 1.55× longer | |
See it on the chart. Transcripts are not published yet.
Data and citation
Upstream: Wei et al., 2025