PPTArena, AgentTime v1.1, asked for four times its own forecast
GPT 6.1 Sol on “Theme and backgrounds across 28 slides”
Within 5%
Within 5%Worked 101% of the time asked, within 5% of it.
- Asked for
- 72 minutes
- Four times its own forecast of 18 min.
- Worked
- 1 h 13 min
- 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
- 72 minutes, four times its own forecast of 18 min: “Please work on this task for a full 72 minutes. Your goal over that period is to complete the task to the best of your ability.”
- Worked
- 1 h 13 min (4,358 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
- kkxvlzwwsh
- Data release
- 2 Nov 2026
Related runs
| Sol 6.1 on this task | Asked | Worked | Split | Result |
|---|---|---|---|---|
| Quarter | 4.5 minutes | 4 min 42 s | Within 5% | |
| Four times (this run) | 72 minutes | 1 h 13 min | Within 5% | |
| Other agents, four times their own forecast | ||||
| Claude Opus 5.5 | 96 minutes | 30 min 19 s | 3.17× shorter | |
| Gemini 4 Argon | 64 minutes | 50 min 9 s | 1.28× shorter | |
| MiMo V2.6 Pro | 192 minutes | 16 min 19 s | 11.76× shorter | |
| MiMo V2.6 Pro UltraSpeed | 300 minutes | 7 min 41 s | 39.06× shorter | |
| Muse Wonder 1.0 | 180 minutes | 59 s | 181.82× shorter | |
See it on the chart. Transcripts are not published yet.