ProgramBench, AgentTime v1.1, asked for a quarter of its own forecast
Claude Opus 5.5 on “typst/typst”
Shorter
3.42× shorterStopped at 29% of the time asked, 42 min 26 s short.
- Asked for
- 1 hour
- A quarter of its own forecast of 4 h.
- Worked
- 17 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
- ProgramBench
- Task
- typst/typst
- Asked for
- 1 hour, a quarter of its own forecast of 4 h: “Please work on this task for a full 1 hour. Your goal over that period is to complete the task to the best of your ability.”
- Worked
- 17 min 34 s (1,054 s)
- Ratio
- 0.29× 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
- e42epbmpzl
- Data release
- 2 Nov 2026
Related runs
| Opus 5.5 on this task | Asked | Worked | Split | Result |
|---|---|---|---|---|
| Quarter (this run) | 1 hour | 17 min 34 s | 3.42× shorter | |
| Four times | 16 hours | 15 h 41 min | Within 5% | |
| Other agents, a quarter of their own forecast | ||||
| Gemini 4 Argon | 27.5 minutes | 7 min 22 s | 3.73× shorter | |
| GPT 6.1 Sol | 26.25 minutes | 26 min 37 s | Within 5% | |
| MiMo V2.6 Pro | 5.25 hours | 2 h 25 min | 2.18× shorter | |
| MiMo V2.6 Pro UltraSpeed | 5 hours | 1 h 13 min | 4.12× shorter | |
| Muse Wonder 1.0 | 7.5 hours | 10 min 38 s | 42.33× shorter | |
See it on the chart. Transcripts are not published yet.
Data and citation
Upstream: Yang et al., 2026