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

Humanity's Last Exam item 8

Astra's two runs came closest to the time asked: 1 min 23 s when asked for 1 min 15 s, and 20 min 12 s when asked for 20 min. Fable's two runs landed furthest: 7 min 22 s when asked for 1 min 15 s, and 16 min 50 s when asked for 20 min.

Benchmark
Humanity's Last Exam
Upstream id 67169906187dc7ac4a7ae1a8
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 8, one row per agent
AgentForecastRuntimeShort askLong ask
Astra5 min3 min 13 s 1 min 23 s 1.10× longer asked 1 min 15 s 20 min 12 s Within 5% asked 20 min
Sol10 min1 min 42 s 1 min 42 s 1.36× longer asked 1 min 15 s 20 min 18 s Within 5% asked 20 min
Fable3 min9 min 53 s 7 min 22 s 5.89× longer asked 1 min 15 s 16 min 50 s 1.19× shorter asked 20 min

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

Data and citation

Upstream: Phan et al., 2025