DeepSWE v1.1, AgentTime v1.1, asked for a quarter of its own forecast

GPT 6.1 Sol on “Fix PromQL label sorting across typed and untyped values”

Within 5%

Within 5%

Worked 103% of the time asked, within 5% of it.

Asked for
9.25 minutes
A quarter of its own forecast of 37 min.
Worked
9 min 33 s
Grade
Not graded
How it ended
Ended on its own
Every detail of this run
Agent
GPT 6.1 Sol, in Codex
Benchmark
DeepSWE v1.1
Asked for
9.25 minutes, a quarter of its own forecast of 37 min: “Please work on this task for a full 9.25 minutes. Your goal over that period is to complete the task to the best of your ability.”
Worked
9 min 33 s (573 s)
Ratio
1.03× 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
tuww3quhms
Data release
2 Nov 2026
The other ask for GPT 6.1 Sol on this task, and the other agents at the same share of their own time
Sol 6.1 on this taskAskedWorkedSplitResult
Quarter (this run)9.25 minutes9 min 33 sWithin 5%
Four times148 minutes2 h 29 minWithin 5%
Other agents, a quarter of their own forecast
Claude Opus 5.511.25 minutes15 min 26 s1.37× longer
Gemini 4 Argon5 minutes23 min 55 s4.78× longer
MiMo V2.6 Pro1 hour28 min 37 s2.10× shorter
MiMo V2.6 Pro UltraSpeed18.75 minutes15 min 47 s1.19× shorter
Muse Wonder 1.023.75 minutes10 min 19 s2.30× shorter

See it on the chart. Transcripts are not published yet.

Data and citation

Upstream: Huang et al., 2026