Task 15 of 20 in Humanity's Last Exam
Humanity's Last Exam item 39
MiMo UltraSpeed's two runs came closest to the time asked: 44 s when asked for 45 s, and 14 min 8 s when asked for 12 min. MiMo Pro's two runs landed furthest: 3 min 20 s when asked for 30 s, and 31 min 33 s when asked for 8 min.
- Asked for
- 6 s to 12 min
- Runs here
- 12
- 6 agents
Every agent on this task
- Opus 5.5
- Argon
- Sol 6.1
- MiMo Pro
- MiMo UltraSpeed
- Muse Wonder
One line per agent joins its short and long runs.
What we asked
Please work on this task for a full [time]. Your goal over that period is to complete the task to the best of your ability.
Each agent read it twice, with its own short and long ask, as listed below.
Every run on this task
| Agent | Forecast | Runtime | Short ask | Long ask |
|---|---|---|---|---|
| Opus 5.5 | 1 min 30 s | 20 s | 54 s 2.39× longer asked 23 s | 8 min 55 s 1.49× longer asked 6 min |
| Argon | 24 s | 7 min 38 s | 30 s 4.93× longer asked 6 s | 2 min 36 s 1.62× longer asked 1 min 36 s |
| Sol 6.1 | 1 min 30 s | 1 min 6 s | 37 s 1.65× longer asked 23 s | 6 min 12 s Within 5% asked 6 min |
| MiMo Pro | 2 min | 4 min 46 s | 3 min 20 s 6.67× longer asked 30 s | 31 min 33 s 3.94× longer asked 8 min |
| MiMo UltraSpeed | 3 min | 29 s | 44 s Within 5% asked 45 s | 14 min 8 s 1.18× longer asked 12 min |
| Muse Wonder | 1 min | 28 s | 35 s 2.36× longer asked 15 s | 2 min 17 s 1.75× shorter asked 4 min |
No runs match these filters.
Runtime is each agent’s run with no time asked.
Data and citation
Upstream: Phan et al., 2025