all the models — AI benchmark observatory
← Benchmarks

MRCR 64K (4-needle)

MRCR (Multi-Round Coreference Resolution) at 64K context length with 4 needles. Models must navigate long conversations to reproduce specific model outputs, testing attention and reasoning across 64K-token contexts with 4 items to retrieve.

id mrcr-64k-(4-needle) · max 1 · 1 models reported

#ModelScore

No scores for this benchmark yet.