long context benchmark
MRCR v2
MRCR v2 (Multi-Round Coreference Resolution version 2) is an enhanced version of the synthetic long-context reasoning task. It extends the original MRCR framework with improved evaluation criteria and additional complexity for testing models' ability to maintain attention and reasoning across extended contexts.
Updated Aug 11, 2026
Models3
Model coverage3
MetricScore
EvidenceB
MRCR v2 Ranking
Higher score ranks better on this benchmark.
| 1 | AC | 91.7% | 100.0% | 3 | C | |
| 2 | GO | 32.0% | 50.0% | 3 | C | |
| 3 | GO | 16.6% | 0.0% | 3 | C |
MRCR v2 Score Distribution
A closer view of the leading scores on this benchmark.
MRCR v2 Highlights
The leading models and scores on this benchmark.
What is MRCR v2?
What MRCR v2 measures and how its scores work.
MRCR v2 (Multi-Round Coreference Resolution version 2) is an enhanced version of the synthetic long-context reasoning task. It extends the original MRCR framework with improved evaluation criteria and additional complexity for testing models' ability to maintain attention and reasoning across extended contexts.
Scores are shown in ratio. This benchmark is not independently verified and has an evidence level of B.
- Family
- MRCR v2
- Modality
- text
- Primary category
- long context
- Score direction
- higher
- LLMBoard eligible
- Yes
- Evaluation key
- mrcr-v2|llm-stats-current
Benchmark scores retain their original unit. Overall score eligibility is shown separately.
FAQ
Common questions about MRCR v2.
Which model scores highest on MRCR v2?
Qwen3.7-Plus is currently ranked first with 91.7%.
What does MRCR v2 measure?
MRCR v2 (Multi-Round Coreference Resolution version 2) is an enhanced version of the synthetic long-context reasoning task. It extends the original MRCR framework with improved evaluation criteria and additional complexity for testing models' ability to maintain attention and reasoning across extended contexts.
Is a higher score better?
Yes. Higher values rank better for this benchmark.
How many models are compared?
3 model results are currently shown.
Does this benchmark affect the overall score?
Yes. This benchmark can contribute to the current LLMBoard capability score.