long context benchmark
MRCR 1M Leaderboard
MRCR 1M is a Multi-Round Coreference Resolution benchmark variant for testing extremely long context capabilities with approximately 1 million tokens.
Updated Sep 5, 2026
Models4
Model coverage4
MetricScore
EvidenceB
MRCR 1M Ranking
Higher score ranks better on this benchmark.
Sort by
Rank | Model | Score | Percentile | Participants | Evidence | Evaluated |
|---|
| Rank01 | ModelDE | Score83.50% | Percentile100.00% | Participants4 | EvidenceC | Evaluated |
| Rank02 | ModelDE | Score78.70% | Percentile66.67% | Participants4 | EvidenceC | Evaluated |
| Rank03 | ModelDE | Score76.90% | Percentile33.33% | Participants4 | EvidenceC | Evaluated |
| Rank04 | ModelGO | Score58.00% | Percentile0.00% | Participants4 | EvidenceC | Evaluated |
MRCR 1M Highlights
The leading models and scores on this benchmark.
MRCR 1M Score Distribution
A closer view of the leading scores on this benchmark.
The Top AI Models for MRCR 1M
The first five results on this benchmark, with official price and output speed added where the model identity can be matched.
What is MRCR 1M?
What MRCR 1M measures and how its scores work.
MRCR 1M is a variant of the Multi-Round Coreference Resolution benchmark designed for approximately 1 million-token contexts.
It measures models' ability to maintain reasoning and attention across ultra-long conversations, reported as a Score ratio.
Scores are shown in ratio. This benchmark is not independently verified and has an evidence level of B.
- Family
- MRCR 1M
- Modality
- text
- Primary category
- long context
- Score direction
- higher
- LLMBoard eligible
- No
- Evaluation key
- overall
LLM Stats. Benchmark scores retain their original unit. Overall score eligibility is shown separately.
FAQ
Common questions about MRCR 1M.
Which model scores highest on MRCR 1M?
DeepSeek-V4-Pro-Max is currently ranked first with 83.50%.
What are the top three models on MRCR 1M?
The current leaders are DeepSeek-V4-Pro-Max (83.50%), DeepSeek-V4-Flash-Max (78.70%), and DeepSeek-V4-Flash-0423 (76.90%).
Which MRCR 1M model has the lowest official input price?
DeepSeek-V4-Flash-Max has the lowest matched official input price at $0.14 input / $0.28 output per 1M tokens.
Which models are fastest among MRCR 1M results?
The fastest matched records are Gemini 2.0 Flash-Lite (85.00 tok/s via Google).
Does the highest score result prove overall model quality?
No. This benchmark measures one defined capability or task. The overall LLMBoard score uses a separate aggregation across eligible benchmark evidence.