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

Claude Opus 5.5 on “Add server-sent-event streaming endpoints to Effect HttpApi”

Shorter

1.28× shorter

Stopped at 78% of the time asked, 43 min 12 s short.

Asked for
200 minutes
Four times its own forecast of 50 min.
Worked
2 h 37 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
200 minutes, four times its own forecast of 50 min: “Please work on this task for a full 200 minutes. Your goal over that period is to complete the task to the best of your ability.”
Worked
2 h 37 min (9,408 s)
Ratio
0.78× 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
6huztwio6p
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
Quarter12.5 minutes4 min 5 s3.06× shorter
Four times (this run)200 minutes2 h 37 min1.28× shorter
Other agents, four times their own forecast
Gemini 4 Argon128 minutes1 h 6 min1.95× shorter
GPT 6.1 Sol280 minutes4 h 41 minWithin 5%
MiMo V2.6 Pro460 minutes41 min 15 s11.15× shorter
MiMo V2.6 Pro UltraSpeed720 minutes28 min 13 s25.51× shorter
Muse Wonder 1.0840 minutes29 min 25 s28.55× shorter

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

Data and citation

Upstream: Huang et al., 2026