PaperBench, AgentTime v1.1, asked for four times its runtime with no time asked
GPT 6.1 Sol on “BAM”
Within 5%
Within 5%Worked 105% of the time asked, within 5% of it.
- Asked for
- 194 minutes
- Four times its runtime with no time asked (48 min 34 s).
- Worked
- 3 h 23 min
- Grade
- Not graded
- How it ended
- Ended on its own
Every detail of this run
- Agent
- GPT 6.1 Sol, in Codex
- Benchmark
- PaperBench
- Task
- BAM
- Asked for
- 194 minutes, four times its runtime with no time asked (48 min 34 s): “Please work on this task for a full 194 minutes. Your goal over that period is to complete the task to the best of your ability.”
- Worked
- 3 h 23 min (12,193 s)
- Ratio
- 1.05× 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
- bbo354c5x6
- Data release
- 2 Nov 2026
Related runs
| Sol 6.1 on this task | Asked | Worked | Split | Result |
|---|---|---|---|---|
| Quarter | 12.1 minutes | 12 min 19 s | Within 5% | |
| Four times (this run) | 194 minutes | 3 h 23 min | Within 5% | |
| Other agents, four times their own runtime | ||||
| Claude Opus 5.5 | 20.2 hours | 5 h 9 min | 3.92× shorter | |
| Gemini 4 Argon | 370 minutes | 2 h 26 min | 2.54× shorter | |
| MiMo V2.6 Pro | 43.9 hours | 4 h 48 min | 9.15× shorter | |
| MiMo V2.6 Pro UltraSpeed | 370 minutes | 3 h 41 min | 1.67× shorter | |
See it on the chart. Transcripts are not published yet.
Data and citation
Upstream: Starace et al., 2025