CORE-Bench v1.1, AgentTime v1.1, asked for four times its own forecast
Claude Opus 5.5 on “Run a quantum measurement and tomography toolbox”
Shorter
5.22× shorterStopped at 19% of the time asked, 32 min 20 s short.
- Asked for
- 40 minutes
- Four times its own forecast of 10 min.
- Worked
- 7 min 40 s
- Grade
- Not graded
- How it ended
- Ended on its own
Every detail of this run
- Agent
- Claude Opus 5.5, in Claude Code
- Benchmark
- CORE-Bench v1.1
- Asked for
- 40 minutes, four times its own forecast of 10 min: “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
- 7 min 40 s (460 s)
- Ratio
- 0.19× the request
- How it ended
- Ended on its own
- Grade
- Not graded
- Clock tool
- The agent could call a wall-clock tool to read the current time.
- Wording
- The paper's standard sentence, sent in AgentTime v1.1.
- Run id
- chcfsk64vy
- Data release
- 2 Nov 2026
Related runs
| Opus 5.5 on this task | Asked | Worked | Split | Result |
|---|---|---|---|---|
| Quarter | 2.5 minutes | 1 min 48 s | 1.39× shorter | |
| Four times (this run) | 40 minutes | 7 min 40 s | 5.22× shorter | |
| Other agents, four times their own forecast | ||||
| Gemini 4 Argon | 20 minutes | 21 min 11 s | 1.06× longer | |
| GPT 6.1 Sol | 40 minutes | 40 min 29 s | Within 5% | |
| MiMo V2.6 Pro | 240 minutes | 9 min 59 s | 24.02× shorter | |
| MiMo V2.6 Pro UltraSpeed | 220 minutes | 5 min 59 s | 36.79× shorter | |
| Muse Wonder 1.0 | 192 minutes | 1 min 33 s | 123.87× shorter | |
See it on the chart. Transcripts are not published yet.
Data and citation
Upstream: Nadgir et al., 2026