DeepSWE v1.1, AgentTime v1.1, asked for a quarter of its own forecast
Claude Opus 5.5 on “Add scoped state data to state-machine callbacks and history”
Shorter
1.46× shorterStopped at 69% of the time asked, 3 min 56 s short.
- Asked for
- 12.5 minutes
- A quarter of its own forecast of 50 min.
- Worked
- 8 min 34 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
- 12.5 minutes, a quarter of its own forecast of 50 min: “Please work on this task for a full 12.5 minutes. Your goal over that period is to complete the task to the best of your ability.”
- Worked
- 8 min 34 s (514 s)
- Ratio
- 0.69× 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
- ihuhz4rj7b
- Data release
- 2 Nov 2026
Related runs
| Opus 5.5 on this task | Asked | Worked | Split | Result |
|---|---|---|---|---|
| Quarter (this run) | 12.5 minutes | 8 min 34 s | 1.46× shorter | |
| Four times | 200 minutes | 2 h 14 min | 1.49× shorter | |
| Other agents, a quarter of their own forecast | ||||
| Gemini 4 Argon | 9.5 minutes | 44 min 58 s | 4.73× longer | |
| GPT 6.1 Sol | 16.25 minutes | 16 min 33 s | Within 5% | |
| MiMo V2.6 Pro | 1.125 hours | 26 min 11 s | 2.58× shorter | |
| MiMo V2.6 Pro UltraSpeed | 1.5 hours | 12 min 50 s | 7.01× shorter | |
| Muse Wonder 1.0 | 50 minutes | 19 min 19 s | 2.59× shorter | |
See it on the chart. Transcripts are not published yet.
Data and citation
Upstream: Huang et al., 2026