← Benchmarks
MRCR v2 (8-needle)
MRCR v2 (8-needle) is a variant of the Multi-Round Coreference Resolution benchmark that includes 8 needle items to retrieve from long contexts. This tests models' ability to simultaneously track and reason about multiple pieces of information across extended conversations.
id mrcr-v2-(8-needle) · max 1 · 25 models reported
| # | Model | Score |
|---|---|---|
| 1 | Muse Spark 1.3 Meta | 0.98 |
| 2 | Gemini 3.7 Flash Google | 0.97 |
| 3 | Qwen3.8 Max Alibaba Cloud / Qwen Team · open | 0.93 |
