reasoning 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 7, 2026
Published models3
Registry coverage3
MetricScore
EvidenceB
MRCR v2 leaderboard
Sorted by the source-provided rank. Higher score is better according to the registry.
| 1 | AC | 91.7% | 100.0% | 3 | C | |
| 2 | GO | 32.0% | 50.0% | 3 | C | |
| 3 | GO | 16.6% | 0.0% | 3 | C |
Score distribution
Top published rows on the benchmark's original scale.
MRCR v2 highlights
The top published results on this benchmark's own scale.
What is MRCR v2?
Definition and scoring fields from the benchmark registry.
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. The current registry marks this benchmark as not independently verified with evidence level B.
- Family
- MRCR v2
- Modality
- text
- Primary category
- reasoning
- Score direction
- higher
- LLMBoard eligible
- No
- Evaluation key
- mrcr-v2|llm-stats-current
Source-native results are preserved. Eligibility for the overall LLMBoard score is a separate policy decision.
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 unique published model results are currently shown.
Does this benchmark affect the overall score?
This benchmark is preserved as source-native evidence but is not eligible for the current overall score.