DeepSWE v1.1, AgentTime v1.1, asked for a quarter of its own forecast
Claude Opus 5.5 on “Add duration-aware sharding to Vitest”
Shorter
2.56× shorterStopped at 39% of the time asked, 6 min 51 s short.
- Asked for
- 11.25 minutes
- A quarter of its own forecast of 45 min.
- Worked
- 4 min 24 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
- DeepSWE v1.1
- Asked for
- 11.25 minutes, a quarter of its own forecast of 45 min: “Please work on this task for a full 11.25 minutes. Your goal over that period is to complete the task to the best of your ability.”
- Worked
- 4 min 24 s (264 s)
- Ratio
- 0.39× 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
- 4okxsg42gz
- Data release
- 2 Nov 2026
Related runs
| Opus 5.5 on this task | Asked | Worked | Split | Result |
|---|---|---|---|---|
| Quarter (this run) | 11.25 minutes | 4 min 24 s | 2.56× shorter | |
| Four times | 180 minutes | 1 h 44 min | 1.73× shorter | |
| Other agents, a quarter of their own forecast | ||||
| Gemini 4 Argon | 8.75 minutes | 18 min 24 s | 2.10× longer | |
| GPT 6.1 Sol | 10.5 minutes | 10 min 54 s | Within 5% | |
| MiMo V2.6 Pro | 37.5 minutes | 27 min 51 s | 1.35× shorter | |
| MiMo V2.6 Pro UltraSpeed | 1.25 hours | 25 min 25 s | 2.95× shorter | |
| Muse Wonder 1.0 | 33.75 minutes | 5 min 51 s | 5.77× shorter | |
See it on the chart. Transcripts are not published yet.
Data and citation
Upstream: Huang et al., 2026