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

GPT 6.1 Sol on “Add duration-aware sharding to Vitest”

Within 5%

Within 5%

Worked 101% of the time asked, within 5% of it.

Asked for
168 minutes
Four times its own forecast of 42 min.
Worked
2 h 49 min
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
168 minutes, four times its own forecast of 42 min: “Please work on this task for a full 168 minutes. Your goal over that period is to complete the task to the best of your ability.”
Worked
2 h 49 min (10,131 s)
Ratio
1.01× 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
q5zk6pm2ah
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
Quarter10.5 minutes10 min 54 sWithin 5%
Four times (this run)168 minutes2 h 49 minWithin 5%
Other agents, four times their own forecast
Claude Opus 5.5180 minutes1 h 44 min1.73× shorter
Gemini 4 Argon140 minutes33 min 22 s4.20× shorter
MiMo V2.6 Pro600 minutes27 min 57 s21.47× shorter
MiMo V2.6 Pro UltraSpeed20 hours24 min 46 s48.45× shorter
Muse Wonder 1.0540 minutes8 min 25 s64.13× shorter

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

Data and citation

Upstream: Huang et al., 2026