PostTrainBench v1.1, AgentTime v1.1, asked for four times its runtime with no time asked
GPT 6.1 Sol on “Post-train Qwen3-1.7B-Base for GSM8K”
Within 5%
Within 5%Worked 100% of the time asked, within 5% of it.
- Asked for
- 762 minutes
- Four times its runtime with no time asked (3 h 10 min).
- Worked
- 12 h 43 min
- 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
- 762 minutes, four times its runtime with no time asked (3 h 10 min): “Please work on this task for a full 762 minutes. Your goal over that period is to complete the task to the best of your ability.”
- Worked
- 12 h 43 min (45,766 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
- tbnpbk2j7o
- Data release
- 2 Nov 2026
Related runs
| Sol 6.1 on this task | Asked | Worked | Split | Result |
|---|---|---|---|---|
| Quarter | 47.6 minutes | 48 min 21 s | Within 5% | |
| Four times (this run) | 762 minutes | 12 h 43 min | Within 5% | |
| Other agents, four times their own runtime | ||||
| Claude Opus 5.5 | 77.6 hours | 23 h 20 min | 3.33× shorter | |
| Gemini 4 Argon | 21.7 hours | 4 h 8 min | 5.25× shorter | |
| MiMo V2.6 Pro | 803 minutes | 26 h 46 min | 2.00× longer | |
| MiMo V2.6 Pro UltraSpeed | 249 seconds | 8 min 18 s | 2.00× longer | |
See it on the chart. Transcripts are not published yet.
Data and citation
Upstream: Rank et al., 2026 (ICML)