SuperGPQA is a new benchmark that tests LLMs on graduate questions from 285 disciplines after human-LLM filtering, with current best models scoring 61.82 percent.
• Incorrect statements should be somewhat misleading, avoiding obvious or easily dismissible errors
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
SuperGPQA: Scaling LLM Evaluation across 285 Graduate Disciplines
SuperGPQA is a new benchmark that tests LLMs on graduate questions from 285 disciplines after human-LLM filtering, with current best models scoring 61.82 percent.