MRCR 128K (2-needle)
Progress Over Time
Interactive timeline showing model performance evolution on MRCR 128K (2-needle)
MRCR 128K (2-needle) Leaderboard
| Context | Cost | License | ||||
|---|---|---|---|---|---|---|
| 1 |  OpenBMB | 9B | — | — |
What is MRCR 128K (2-needle)?
MRCR (Multi-Round Coreference Resolution) at 128K context length with 2 needles. Models must navigate long conversations to reproduce specific model outputs, testing attention and reasoning across 128K-token contexts with 2 items to retrieve.
MRCR 128K (2-needle) is a text benchmark evaluating models on long context, reasoning, and general tasks. LLM Stats tracks 1 models on this benchmark, scored on a 0–1 scale. The current average is 0.3, with the leader at 0.3.
Compare leaders on the best AI for long context, best AI for reasoning and best AI for general leaderboards.
Current leaders
MiniCPM-SALA from OpenBMB currently leads the MRCR 128K (2-needle) leaderboard with a score of 0.286 across 1 evaluated AI models.
FAQ
Common questions about the MRCR 128K (2-needle) benchmark and leaderboard.