A Humanity's Last Exam task from the paper, not in v1.1

Humanity's Last Exam item 7

Astra's two runs came closest to the time asked: 1 min 29 s when asked for 1 min 15 s, and 20 min 10 s when asked for 20 min. Fable worked about the same whatever it was asked: 5 min 40 s when asked for 1 min 15 s, and 7 min 58 s when asked for 20 min.

Benchmark
Humanity's Last Exam
Upstream id 66fcf48f6da31bbbe3d17e72
Asked for
1 min 15 s to 20 min
Runs here
6
3 agents

Every agent on this task

  • Astra
  • Sol
  • Fable

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

Every run on Humanity's Last Exam item 7, one row per agent
AgentForecastRuntimeShort askLong ask
Astra2 min3 min 19 s 1 min 29 s 1.18× longer asked 1 min 15 s 20 min 10 s Within 5% asked 20 min
Sol1 min2 min 5 s 2 min 5 s 1.66× longer asked 1 min 15 s 20 min 23 s Within 5% asked 20 min
Fable2 min7 min 13 s 5 min 40 s 4.53× longer asked 1 min 15 s 7 min 58 s 2.51× shorter asked 20 min

Runtime is the paper’s estimate from each agent’s timed runs.

Data and citation

Upstream: Phan et al., 2025