EvalHub
BenchmarksModelsDocs
Sign in

Benchmarks

Request a benchmark
All 19knowledge 2coding 10agentic 1legal 2finance 1health 1science 1vision 1
  • Humanity's Last Exam

    v3

    2,500 expert-written closed-ended questions across dozens of subjects (multiple-choice and exact-match, ~14% with images), graded by an LLM judge. Official CAIS harness.

    knowledgeqa8 subsets2,500 samplesvision
  • Humanity's Last Exam: Diamond

    v2

    1,000 refined HLE questions, 500 reasoning and 500 knowledge, graded by an LLM judge. Official CAIS harness, no tools.

    knowledgeqa2 subsets1,000 samplesvision