YC-Bench, AgentTime v1.1, asked for four times its own forecast
GPT 6.1 Sol on “Run the current one-year startup simulation, official seed 2”
Within 5%
Within 5%Worked 100% of the time asked, within 5% of it.
- Asked for
- 240 minutes
- Four times its own forecast of 1 h.
- Worked
- 4 h
- 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
- 240 minutes, four times its own forecast of 1 h: “Please work on this task for a full 240 minutes. Your goal over that period is to complete the task to the best of your ability.”
- Worked
- 4 h (14,410 s)
- Ratio
- 1.00× 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
- l65q3h46lj
- Data release
- 2 Nov 2026
Related runs
| Sol 6.1 on this task | Asked | Worked | Split | Result |
|---|---|---|---|---|
| Quarter | 15 minutes | 15 min 17 s | Within 5% | |
| Four times (this run) | 240 minutes | 4 h | Within 5% | |
| Other agents, four times their own forecast | ||||
| Claude Opus 5.5 | 480 minutes | 1 h 30 min | 5.36× shorter | |
| Gemini 4 Argon | 128 minutes | 2 h 44 min | 1.28× longer | |
| MiMo V2.6 Pro | 800 minutes | 1 h 15 min | 10.67× shorter | |
| MiMo V2.6 Pro UltraSpeed | 360 minutes | 1 h 11 min | 5.08× shorter | |
| Muse Wonder 1.0 | 440 minutes | 18 min 11 s | 24.19× shorter | |
See it on the chart. Transcripts are not published yet.
Data and citation
Upstream: He et al., 2026