DeepSWE v1.1, AgentTime v1.1, asked for four times its own forecast

Claude Opus 5.5 on “Preserve structure needed by stylesheet selectors in OXVG”

Shorter

1.26× shorter

Stopped at 79% of the time asked, 1 h 11 min short.

Asked for
340 minutes
Four times its own forecast of 1 h 25 min.
Worked
4 h 29 min
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
340 minutes, four times its own forecast of 1 h 25 min: “Please work on this task for a full 340 minutes. Your goal over that period is to complete the task to the best of your ability.”
Worked
4 h 29 min (16,144 s)
Ratio
0.79× 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
ptdwv2h6xn
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
Quarter21.25 minutes16 min 19 s1.30× shorter
Four times (this run)340 minutes4 h 29 min1.26× shorter
Other agents, four times their own forecast
Gemini 4 Argon180 minutes2 h 25 min1.25× shorter
GPT 6.1 Sol152 minutes2 h 33 minWithin 5%
MiMo V2.6 Pro16 hours55 min 7 s17.42× shorter
MiMo V2.6 Pro UltraSpeed20 hours49 min 26 s24.28× shorter
Muse Wonder 1.0460 minutes48 min 12 s9.54× shorter

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

Data and citation

Upstream: Huang et al., 2026