PostTrainBench v1.1, AgentTime v1.1, asked for a quarter of its runtime with no time asked
GPT 6.1 Sol on “Post-train Qwen3-1.7B-Base for American Invitational Mathematics Examination (AIME) 2025”
Within 5%
Within 5%Worked 101% of the time asked, within 5% of it.
- Asked for
- 56.4 minutes
- A quarter of its runtime with no time asked (3 h 46 min).
- Worked
- 57 min 7 s
- Grade
- Not graded
- How it ended
- Ended on its own
Every detail of this run
- Agent
- GPT 6.1 Sol, in Codex
- Benchmark
- PostTrainBench v1.1
- Asked for
- 56.4 minutes, a quarter of its runtime with no time asked (3 h 46 min): “Please work on this task for a full 56.4 minutes. Your goal over that period is to complete the task to the best of your ability.”
- Worked
- 57 min 7 s (3,427 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
- tts7lokvmi
- Data release
- 2 Nov 2026
Related runs
| Sol 6.1 on this task | Asked | Worked | Split | Result |
|---|---|---|---|---|
| Quarter (this run) | 56.4 minutes | 57 min 7 s | Within 5% | |
| Four times | 902 minutes | 15 h 3 min | Within 5% | |
| Other agents, a quarter of their own runtime | ||||
| Claude Opus 5.5 | 4.87 hours | 4 h 33 min | 1.07× shorter | |
| Gemini 4 Argon | 1.45 hours | 1 h 31 min | Within 5% | |
| MiMo V2.6 Pro | 5.25 minutes | 1 h 29 min | 16.98× longer | |
| MiMo V2.6 Pro UltraSpeed | 21.4 seconds | 4 min 45 s | 13.30× longer | |
See it on the chart. Transcripts are not published yet.
Data and citation
Upstream: Rank et al., 2026 (ICML)