CORE-Bench v1.1, shortest of three requests
GPT 5.6 Sol on “Run a continuous-time intelligent-reflecting-surface propagation model”
Longer
3.57× longerWorked 257% past the request, 10 min 17 s over.
- Asked for
- 4 minutes
- Worked
- 14 min 17 s
- Grade
- Did not pass
- Score 0 of 100. Graded during the run.
- How it ended
- Ended on its own
Every detail of this run
- Agent
- GPT 5.6 Sol, in Codex
- Benchmark
- CORE-Bench v1.1
- Asked for
- 4 minutes: “Please work on this task for a full 4 minutes. Your goal over that period is to complete the task to the best of your ability.”
- Worked
- 14 min 17 s (857 s)
- Ratio
- 3.57× 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
- es6ryb47qy
- Data release
- 26 Sep 2026
Related runs
| Sol on this task | Asked | Worked | Split | Result |
|---|---|---|---|---|
| Shortest (this run) | 4 minutes | 14 min 17 s | 3.57× longer | |
| Middle | 15 minutes | 15 min 32 s | Within 5% | |
| Longest | 60 minutes | 16 min 56 s | 3.54× shorter | |
| Other agents, shortest request | ||||
| GPT 6 Astra | 4 minutes | 4 min 11 s | Within 5% | |
| Claude Fable 5.1 | 4 minutes | 17 min 47 s | 4.44× longer | |
See it on the chart. Transcripts are not published yet.
Data and citation
Upstream: Nadgir et al., 2026