PaperBench, longest of three requests

GPT 6 Astra on “BAM”

Within 5%

Within 5%

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

Asked for
80 minutes
Worked
1 h 21 min
Grade
Score 0 of 100
Nothing to grade, counted as 0.
How it ended
Ended on its own
Every detail of this run
Agent
GPT 6 Astra, in Codex
Benchmark
PaperBench
Task
BAM
Asked for
80 minutes: “Please work on this task for a full 80 minutes. Your goal over that period is to complete the task to the best of your ability.”
Worked
1 h 21 min (4,833 s)
Ratio
1.01× the request
How it ended
Ended on its own
Grade
0
Replication score: a weighted rubric of pass/fail leaf checks, 0 to 1, after a full reproduction attempt. No official pass rule.
Score
0 of 100
Nothing to grade, counted as 0. The paper's value.
Wording
The standard sentence, used from 4 September 2026.
Run id
dmudbd6km7
Data release
26 Sep 2026
The other requests for GPT 6 Astra on this task, and the other agents at this request
Astra on this taskAskedWorkedSplitResult
Shortest5 minutes5 min 8 sWithin 5%
Middle20 minutes20 min 10 sWithin 5%
Longest (this run)80 minutes1 h 21 minWithin 5%
Other agents, longest request
GPT 5.6 Sol80 minutes1 h 31 min1.14× longer
Claude Fable 5.180 minutes22 min 1 s3.63× shorter

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

Data and citation

Upstream: Starace et al., 2025