long context benchmark
MRCR 128K (2-needle) Leaderboard
MRCR (Multi-Round Coreference Resolution) at 128K context length with 2 needles requires models to navigate long conversations and reproduce specific model outputs.
Updated Sep 5, 2026
Models1
Model coverage1
MetricScore
EvidenceB
MRCR 128K (2-needle) Ranking
Higher score ranks better on this benchmark.
Sort by
Rank | Model | Score | Percentile | Participants | Evidence | Evaluated |
|---|
| Rank01 | ModelOP | Score28.62% | Percentile100.00% | Participants1 | EvidenceC | Evaluated |
MRCR 128K (2-needle) Highlights
The leading models and scores on this benchmark.
The Top AI Models for MRCR 128K (2-needle)
The first five results on this benchmark, with official price and output speed added where the model identity can be matched.
Ranking basisThis mrcr 128k (2-needle) AI model leaderboard uses descending score in the benchmark original unit. The leaderboard ranking keeps matched price and speed data separate from benchmark evidence.
- 01OPOpenBMB
- Score
- 28.62%
Strengths
- Ranks #1 of 1 compared models
- 100th percentile on this benchmark
- C evidence result
Considerations
- This result measures MRCR 128K (2-needle), not total model capability
Selection summary
Best AI Models for MRCR 128K (2-needle)
MiniCPM-SALA currently leads MRCR 128K (2-needle) with 28.62%. It is the top model on this specific benchmark, while the best LLM for the broader task should also be checked against other benchmarks, price, and runtime.
Use this leaderboard with the supporting benchmark results and coverage details above. A leaderboard position summarizes the selected ranking signal; it does not replace workload-specific testing.
What is MRCR 128K (2-needle)?
What MRCR 128K (2-needle) measures and how its scores work.
A long-context benchmark at 128K context length with 2 needles, in which models navigate long conversations to reproduce specific model outputs.
It measures attention and reasoning across 128K-token contexts with 2 items to retrieve.
Scores are shown in ratio. This benchmark is not independently verified and has an evidence level of B.
- Family
- MRCR 128K (2-needle)
- 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 128K (2-needle).
Which model scores highest on MRCR 128K (2-needle)?
MiniCPM-SALA is currently ranked first with 28.62%.
What are the top three models on MRCR 128K (2-needle)?
The current leaders are MiniCPM-SALA (28.62%).
Which MRCR 128K (2-needle) model has the lowest official input price?
No matched official input price is currently available.
Which models are fastest among MRCR 128K (2-needle) results?
No matched runtime record is currently available.
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.