Task 5 of 10 in Sakana ALE-Bench
Future Contest 2022 Qual
Sol 6.1's two runs followed the time asked: 10 min 11 s when asked for 10 min, and 2 h 40 min when asked for 2 h 40 min. Muse Wonder's two runs landed furthest: 4 min 58 s when asked for 52 min 30 s, and 37 min 48 s when asked for 14 h.
- Benchmark
- Sakana ALE-Bench
- Asked for
- 10 min to 24 h
- Runs here
- 18
- See Read before quoting below
Every agent on this task
- Astra
- Sol
- Fable
- 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
No runs match these filters.
Runtime is a v1.1 agent’s run with no time asked, and for the paper’s three agents the paper’s estimate from their timed runs.
Read before quoting. 1 run was stopped by AgentTime, so its time is a lower bound. Details
Data and citation
Upstream: Imajuku et al., 2025