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

GPT 6.1 Sol on “Add server-sent-event streaming endpoints to Effect HttpApi”

Longer

2.65× longer

Worked 165% past the request, 28 min 52 s over.

Asked for
17.5 minutes
A quarter of its own forecast of 1 h 10 min.
Worked
46 min 22 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
17.5 minutes, a quarter of its own forecast of 1 h 10 min: “Please work on this task for a full 17.5 minutes. Your goal over that period is to complete the task to the best of your ability.”
Worked
46 min 22 s (2,782 s)
Ratio
2.65× 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
vf24pexl4o
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)17.5 minutes46 min 22 s2.65× longer
Four times280 minutes4 h 41 minWithin 5%
Other agents, a quarter of their own forecast
Claude Opus 5.512.5 minutes4 min 5 s3.06× shorter
Gemini 4 Argon8 minutes57 min 4 s7.13× longer
MiMo V2.6 Pro28.75 minutes30 min 49 s1.07× longer
MiMo V2.6 Pro UltraSpeed45 minutes23 min 34 s1.91× shorter
Muse Wonder 1.052.5 minutes39 min 16 s1.34× shorter

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

Data and citation

Upstream: Huang et al., 2026