YC-Bench, AgentTime v1.1, asked for four times its own forecast
GPT 6.1 Sol on “Run the canonical one-year startup simulation with seed 4”
Within 5%
Within 5%Worked 104% of the time asked, within 5% of it.
- Asked for
- 200 minutes
- Four times its own forecast of 50 min.
- Worked
- 3 h 28 min
- Grade
- Not graded
- How it ended
- Ended on its own
Every detail of this run
- Agent
- GPT 6.1 Sol, in Codex
- Benchmark
- YC-Bench
- Asked for
- 200 minutes, four times its own forecast of 50 min: “Please work on this task for a full 200 minutes. Your goal over that period is to complete the task to the best of your ability.”
- Worked
- 3 h 28 min (12,466 s)
- Ratio
- 1.04× 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
- xbwb4lhtaa
- Data release
- 2 Nov 2026
Related runs
| Sol 6.1 on this task | Asked | Worked | Split | Result |
|---|---|---|---|---|
| Quarter | 12.5 minutes | 13 min 9 s | 1.05× longer | |
| Four times (this run) | 200 minutes | 3 h 28 min | Within 5% | |
| Other agents, four times their own forecast | ||||
| Claude Opus 5.5 | 440 minutes | 2 h 36 min | 2.82× shorter | |
| Gemini 4 Argon | 100 minutes | 2 h 5 min | 1.25× longer | |
| MiMo V2.6 Pro | 320 minutes | 1 h 25 min | 3.76× shorter | |
| MiMo V2.6 Pro UltraSpeed | 288 minutes | 38 min 58 s | 7.39× shorter | |
| Muse Wonder 1.0 | 380 minutes | 9 min 12 s | 41.30× shorter | |
See it on the chart. Transcripts are not published yet.
Data and citation
Upstream: He et al., 2026