long context benchmark
MRCR 1M (pointwise) Leaderboard
MRCR 1M (pointwise) is a Multi-Round Coreference Resolution benchmark variant for evaluating responses independently in ultra-long contexts of approximately 1M tokens.
Updated Sep 5, 2026
Models1
Model coverage1
MetricScore
EvidenceB
MRCR 1M (pointwise) Ranking
Higher score ranks better on this benchmark.
Sort by
Rank | Model | Score | Percentile | Participants | Evidence | Evaluated |
|---|
| Rank01 | ModelGO | Score82.90% | Percentile100.00% | Participants1 | EvidenceC | Evaluated |
MRCR 1M (pointwise) Highlights
The leading models and scores on this benchmark.
The Top AI Models for MRCR 1M (pointwise)
The first five results on this benchmark, with official price and output speed added where the model identity can be matched.
Ranking basisThis mrcr 1m (pointwise) AI model leaderboard uses descending score in the benchmark original unit. The leaderboard ranking keeps matched price and speed data separate from benchmark evidence.
- 01GOGoogle
- Score
- 82.90%
- Price
- $1.3 input / $10 output per 1M tokens
- Speed
- Up to 18.89 tok/s via Google
Strengths
- Ranks #1 of 1 compared models
- 100th percentile on this benchmark
- C evidence result
Considerations
- This result measures MRCR 1M (pointwise), not total model capability
Selection summary
Best AI Models for MRCR 1M (pointwise)
Gemini 2.5 Pro currently leads MRCR 1M (pointwise) with 82.90%. 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 1M (pointwise)?
What MRCR 1M (pointwise) measures and how its scores work.
MRCR 1M (pointwise) is a long-context benchmark variant that uses pointwise evaluation rather than comparative evaluation.
It measures models' absolute performance on long-context reasoning tasks, with each response evaluated independently, using the Score metric as a ratio.
Scores are shown in ratio. This benchmark is not independently verified and has an evidence level of B.
- Family
- MRCR 1M (pointwise)
- 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 (pointwise).
Which model scores highest on MRCR 1M (pointwise)?
Gemini 2.5 Pro is currently ranked first with 82.90%.
What are the top three models on MRCR 1M (pointwise)?
The current leaders are Gemini 2.5 Pro (82.90%).
Which MRCR 1M (pointwise) model has the lowest official input price?
Gemini 2.5 Pro has the lowest matched official input price at $1.3 input / $10 output per 1M tokens.
Which models are fastest among MRCR 1M (pointwise) results?
The fastest matched records are Gemini 2.5 Pro (18.89 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.