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

Humanity's Last Exam item 5

Astra's two runs came closest to the time asked: 1 min 27 s when asked for 1 min 15 s, and 20 min 12 s when asked for 20 min. Sol's two runs landed furthest: 10 min when asked for 1 min 15 s, and 20 min 15 s when asked for 20 min.

Benchmark
Humanity's Last Exam
Upstream id 66ffaae1068d942d32104650
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 5, one row per agent
AgentForecastRuntimeShort askLong ask
Astra5 min6 min 11 s 1 min 27 s 1.15× longer asked 1 min 15 s 20 min 12 s Within 5% asked 20 min
Sol5 min11 min 27 s 10 min 8.00× longer asked 1 min 15 s 20 min 15 s Within 5% asked 20 min
Fable1 min4 min 2 s 1 min 53 s 1.50× longer asked 1 min 15 s 9 min 15 s 2.16× shorter asked 20 min

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

Data and citation

Upstream: Phan et al., 2025