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

Claude Opus 5.5 on “Add JSON Schema references and dependency keywords to ArkType”

Shorter

4.32× shorter

Stopped at 23% of the time asked, 10 min 34 s short.

Asked for
13.75 minutes
A quarter of its own forecast of 55 min.
Worked
3 min 11 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
13.75 minutes, a quarter of its own forecast of 55 min: “Please work on this task for a full 13.75 minutes. Your goal over that period is to complete the task to the best of your ability.”
Worked
3 min 11 s (191 s)
Ratio
0.23× 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
527sgjei3u
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)13.75 minutes3 min 11 s4.32× shorter
Four times220 minutes3 h 4 min1.20× shorter
Other agents, a quarter of their own forecast
Gemini 4 Argon6.5 minutes55 min 49 s8.59× longer
GPT 6.1 Sol13.75 minutes14 min 1 sWithin 5%
MiMo V2.6 Pro1 hour37 min 14 s1.61× shorter
MiMo V2.6 Pro UltraSpeed18.75 minutes13 min 31 s1.39× shorter
Muse Wonder 1.042.5 minutes24 min 57 s1.70× shorter

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

Data and citation

Upstream: Huang et al., 2026