Agents' Last Exam, AgentTime v1.1, asked for four times its own forecast
GPT 6.1 Sol on “Molecular Structure Plausibility”
Within 5%
Within 5%Worked 101% of the time asked, within 5% of it.
- Asked for
- 48 minutes
- Four times its own forecast of 12 min.
- Worked
- 48 min 37 s
- Grade
- Not graded
- How it ended
- Ended on its own
Every detail of this run
- Agent
- GPT 6.1 Sol, in Codex
- Benchmark
- Agents' Last Exam
- Asked for
- 48 minutes, four times its own forecast of 12 min: “Please work on this task for a full 48 minutes. Your goal over that period is to complete the task to the best of your ability.”
- Worked
- 48 min 37 s (2,917 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
- rwd5xercto
- Data release
- 2 Nov 2026
Related runs
| Sol 6.1 on this task | Asked | Worked | Split | Result |
|---|---|---|---|---|
| Quarter | 3 minutes | 3 min 17 s | 1.09× longer | |
| Four times (this run) | 48 minutes | 48 min 37 s | Within 5% | |
| Other agents, four times their own forecast | ||||
| Claude Opus 5.5 | 60 minutes | 28 min 27 s | 2.11× shorter | |
| Gemini 4 Argon | 32 minutes | 33 min 50 s | 1.06× longer | |
| MiMo V2.6 Pro | 140 minutes | 18 min 16 s | 7.67× shorter | |
| MiMo V2.6 Pro UltraSpeed | 160 minutes | 4 min 7 s | 38.93× shorter | |
| Muse Wonder 1.0 | 140 minutes | 2 min 17 s | 61.40× shorter | |
See it on the chart. Transcripts are not published yet.
Data and citation
Upstream: Sun et al., 2026