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

Claude Opus 5.5 on “Add worktree merge conflict handling”

Longer

2.29× longer

Worked 129% past the request, 12 min 52 s over.

Asked for
10 minutes
A quarter of its own forecast of 40 min.
Worked
22 min 52 s
Grade
Not graded
How it ended
Ended on its own
Every detail of this run
Agent
Claude Opus 5.5, in Claude Code
Benchmark
DeepSWE v1.1
Asked for
10 minutes, a quarter of its own forecast of 40 min: “Please work on this task for a full 10 minutes. Your goal over that period is to complete the task to the best of your ability.”
Worked
22 min 52 s (1,372 s)
Ratio
2.29× 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
lpiwnhtows
Data release
2 Nov 2026
The other ask for Claude Opus 5.5 on this task, and the other agents at the same share of their own time
Opus 5.5 on this taskAskedWorkedSplitResult
Quarter (this run)10 minutes22 min 52 s2.29× longer
Four times160 minutes2 h 15 min1.18× shorter
Other agents, a quarter of their own forecast
Gemini 4 Argon5.5 minutes34 min 29 s6.27× longer
GPT 6.1 Sol16.25 minutes16 min 37 sWithin 5%
MiMo V2.6 Pro1.125 hours23 min 56 s2.82× shorter
MiMo V2.6 Pro UltraSpeed1 hour11 min 49 s5.08× shorter
Muse Wonder 1.045 minutes10 min 14 s4.39× shorter

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

Data and citation

Upstream: Huang et al., 2026