CORE-Bench v1.1, longest of three requests

GPT 5.6 Sol on “Run and render CNN short-term temperature forecasting results”

Shorter

6.98× shorter

Stopped at 14% of the time asked, 51 min 24 s short.

Asked

Worked

Safety cutoff 2 h, off the scale

Every detail of this run

Agent: GPT 5.6 Sol, in Codex
Benchmark: CORE-Bench v1.1
Task: Run and render CNN short-term temperature forecasting results
Asked for: 60 minutes: “Please work on this task for a full 60 minutes. Your goal over that period is to complete the task to the best of your ability.”
Worked: 8 min 36 s (516 s)
Ratio: 0.14× 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: svslj4awwg
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	4 minutes	4 min 54 s	1.23× longer
Middle	15 minutes	15 min 47 s	1.05× longer
Longest (this run)	60 minutes	8 min 36 s	6.98× shorter
Other agents, longest request
GPT 6 Astra	60 minutes	1 h 1 min	Within 5%
Claude Fable 5.1	60 minutes	10 min 13 s	5.87× shorter

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

Data and citation