BrowseComp, AgentTime v1.1, asked for four times its own forecast
Claude Opus 5.5 on “BrowseComp question 1”
Shorter
1.73× shorterStopped at 58% of the time asked, 50 min 41 s short.
- Asked for
- 120 minutes
- Four times its own forecast of 30 min.
- Worked
- 1 h 9 min
- 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
- 120 minutes, four times its own forecast of 30 min: “Please work on this task for a full 120 minutes. Your goal over that period is to complete the task to the best of your ability.”
- Worked
- 1 h 9 min (4,159 s)
- Ratio
- 0.58× 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
- z7rfkmqlso
- Data release
- 2 Nov 2026
Related runs
| Opus 5.5 on this task | Asked | Worked | Split | Result |
|---|---|---|---|---|
| Quarter | 7.5 minutes | 49 min 47 s | 6.64× longer | |
| Four times (this run) | 120 minutes | 1 h 9 min | 1.73× shorter | |
| Other agents, four times their own forecast | ||||
| Gemini 4 Argon | 56 minutes | 56 min 14 s | Within 5% | |
| GPT 6.1 Sol | 100 minutes | 1 h 41 min | Within 5% | |
| MiMo V2.6 Pro | 300 minutes | 1 h 32 min | 3.26× shorter | |
| MiMo V2.6 Pro UltraSpeed | 180 minutes | 10 min 27 s | 17.23× shorter | |
| Muse Wonder 1.0 | 160 minutes | 2 h 31 min | 1.06× shorter | |
See it on the chart. Transcripts are not published yet.
Data and citation
Upstream: Wei et al., 2025