MRCR 1M — leaderboard

MRCR 1M is a variant of the Multi-Round Coreference Resolution benchmark designed for testing extremely long context capabilities with approximately 1 million tokens. It evaluates models' ability to maintain reasoning and attention across ultra-long conversations.

Source: huggingface.co.

Interactive version: theaggregate.ai/benchmark?slug=mrcr-1m · How the rankings work · Data refreshed daily, snapshot 2026-07-22.