AppWorld, shortest of three requests
GPT 5.6 Sol on “Turn a note-based meeting schedule into correctly timed reminder emails”
Shorter
1.20× shorterStopped at 84% of the time asked, 15 s short.
- Asked for
- 1.5 minutes
- Worked
- 1 min 15 s
- Grade
- Passed
- Score 100 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
- AppWorld
- Asked for
- 1.5 minutes: “Please work on this task for a full 1.5 minutes. Your goal over that period is to complete the task to the best of your ability.”
- Worked
- 1 min 15 s (75 s)
- Ratio
- 0.84× the request
- How it ended
- Ended on its own
- Grade
- Passed
- It passed every final-state test. The grader returned 1. Pass rule: Every final-state test passes.
- Score
- 100 of 100
- Graded during the run. The paper's value.
- Wording
- The standard sentence, used from 4 September 2026.
- Run id
- dyknuc4uvx
- Data release
- 26 Sep 2026
Related runs
| Sol on this task | Asked | Worked | Split | Result |
|---|---|---|---|---|
| Shortest (this run) | 1.5 minutes | 1 min 15 s | 1.20× shorter | |
| Middle | 6 minutes | 6 min 39 s | 1.11× longer | |
| Longest | 25 minutes | 26 min 50 s | 1.07× longer | |
| Other agents, shortest request | ||||
| GPT 6 Astra | 1.5 minutes | 1 min 44 s | 1.16× longer | |
| Claude Fable 5.1 | 1.5 minutes | 3 min 10 s | 2.11× longer | |
See it on the chart. Transcripts are not published yet.
Data and citation
Upstream: Trivedi et al., 2024 (ACL)