CORE-Bench v1.1, longest of three requests

GPT 5.6 Sol on “Run product-review sentiment mining and reproduce its metrics”

Longer

1.22× longer

Worked 22% past the request, 8 min 58 s over.

Asked

Worked

Safety cutoff 1 h 20 min, off the scale

Every detail of this run

Agent: GPT 5.6 Sol, in Codex
Benchmark: CORE-Bench v1.1
Task: Run product-review sentiment mining and reproduce its metrics
Asked for: 40 minutes: “Please work on this task for a full 40 minutes. Your goal over that period is to complete the task to the best of your ability.”
Worked: 48 min 58 s (2,938 s)
Ratio: 1.22× the request
How it ended: Ended on its own
Grade: Did not pass; It did not get every answer right. The grader returned 0. Pass rule: Every answer correct, with numbers inside a 95% prediction interval.
Score: 0 of 100; Graded during the run. The paper's value.
Wording: The standard sentence, used from 4 September 2026.
Run id: cs4peqlqg5
Data release: 26 Sep 2026

The other requests for GPT 5.6 Sol on this task, and the other agents at this request
Sol on this task	Asked	Worked	Result
Shortest	2.5 minutes	11 min 34 s	4.63× longer
Middle	10 minutes	14 min 36 s	1.46× longer
Longest (this run)	40 minutes	48 min 58 s	1.22× longer
Other agents, longest request
GPT 6 Astra	40 minutes	44 min 15 s	1.11× longer
Claude Fable 5.1	40 minutes	22 min 22 s	1.79× shorter

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

Data and citation