YC-Bench, AgentTime v1.1, asked for a quarter of its own forecast

Claude Opus 5.5 on “Run the current one-year startup simulation, official seed 3”

Within 5%

Within 5%

Worked 96% of the time asked, within 5% of it.

Asked for
35 minutes
A quarter of its own forecast of 2 h 20 min.
Worked
33 min 45 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
YC-Bench
Asked for
35 minutes, a quarter of its own forecast of 2 h 20 min: “Please work on this task for a full 35 minutes. Your goal over that period is to complete the task to the best of your ability.”
Worked
33 min 45 s (2,025 s)
Ratio
0.96× 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
xihaeoix25
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)35 minutes33 min 45 sWithin 5%
Four times560 minutes2 h 7 min4.40× shorter
Other agents, a quarter of their own forecast
Gemini 4 Argon8.75 minutes9 min 19 s1.06× longer
GPT 6.1 Sol13.75 minutes14 min 46 s1.07× longer
MiMo V2.6 Pro22.5 minutes44 min 11 s1.96× longer
MiMo V2.6 Pro UltraSpeed22.5 minutes8 min 58 s2.51× shorter

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

Data and citation

Upstream: He et al., 2026