PPTArena, AgentTime v1.1, asked for four times its own forecast
GPT 6.1 Sol on “Copernicus climate multi-edit cascade”
Within 5%
Within 5%Worked 101% of the time asked, within 5% of it.
- Asked for
- 30 minutes
- Four times its own forecast of 7 min 30 s.
- Worked
- 30 min 20 s
- Grade
- Not graded
- How it ended
- Ended on its own
Every detail of this run
- Agent
- GPT 6.1 Sol, in Codex
- Benchmark
- PPTArena
- Asked for
- 30 minutes, four times its own forecast of 7 min 30 s: “Please work on this task for a full 30 minutes. Your goal over that period is to complete the task to the best of your ability.”
- Worked
- 30 min 20 s (1,820 s)
- Ratio
- 1.01× 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
- 6xinmrthqy
- Data release
- 2 Nov 2026
Related runs
| Sol 6.1 on this task | Asked | Worked | Split | Result |
|---|---|---|---|---|
| Quarter | 1.875 minutes | 2 min 4 s | 1.10× longer | |
| Four times (this run) | 30 minutes | 30 min 20 s | Within 5% | |
| Other agents, four times their own forecast | ||||
| Claude Opus 5.5 | 52 minutes | 20 min 2 s | 2.60× shorter | |
| Gemini 4 Argon | 22 minutes | 19 min 23 s | 1.13× shorter | |
| MiMo V2.6 Pro | 140 minutes | 14 min 43 s | 9.51× shorter | |
| MiMo V2.6 Pro UltraSpeed | 320 minutes | 8 min 25 s | 38.00× shorter | |
| Muse Wonder 1.0 | 112 minutes | 47 s | 143.59× shorter | |
See it on the chart. Transcripts are not published yet.