long context benchmark
OpenAI-MRCR: 2 needle 128k Leaderboard
OpenAI-MRCR: 2 needle 128k is a Multi-round Co-reference Resolution benchmark for evaluating an LLM's ability to distinguish between multiple needles hidden in a long context.
Updated Sep 5, 2026
Models9
Model coverage9
MetricScore
EvidenceB
OpenAI-MRCR: 2 needle 128k Ranking
Higher score ranks better on this benchmark.
Sort by
Rank | Model | Score | Percentile | Participants | Evidence | Evaluated |
|---|
| Rank01 | ModelOP | Score95.20% | Percentile100.00% | Participants9 | EvidenceC | Evaluated |
| Rank02 | ModelMI | Score76.10% | Percentile87.50% | Participants9 | EvidenceC | Evaluated |
| Rank03 | ModelMI | Score73.40% | Percentile75.00% | Participants9 | EvidenceC | Evaluated |
| Rank04 | ModelOP | Score57.20% | Percentile62.50% | Participants9 | EvidenceC | Evaluated |
| Rank05 | ModelOP | Score47.20% | Percentile50.00% | Participants9 | EvidenceC | Evaluated |
| Rank06 | ModelOP | Score38.50% | Percentile37.50% | Participants9 | EvidenceC | Evaluated |
| Rank07 | ModelOP | Score36.60% | Percentile25.00% | Participants9 | EvidenceC | Evaluated |
| Rank08 | ModelOP | Score31.90% | Percentile12.50% | Participants9 | EvidenceC | Evaluated |
| Rank09 | ModelOP | Score18.70% | Percentile0.00% | Participants9 | EvidenceC | Evaluated |
OpenAI-MRCR: 2 needle 128k Highlights
The leading models and scores on this benchmark.
OpenAI-MRCR: 2 needle 128k Score Distribution
A closer view of the leading scores on this benchmark.
The Top AI Models for OpenAI-MRCR: 2 needle 128k
The first five results on this benchmark, with official price and output speed added where the model identity can be matched.
What is OpenAI-MRCR: 2 needle 128k?
What OpenAI-MRCR: 2 needle 128k measures and how its scores work.
A benchmark using a long, multi-turn synthetic conversation in which models retrieve a specific instance of a repeated request.
It measures the ability to distinguish between multiple needles, retrieve a specific repeated request, and apply reasoning and disambiguation skills, reported as a Score ratio.
Scores are shown in ratio. This benchmark is not independently verified and has an evidence level of B.
- Family
- OpenAI-MRCR: 2 needle 128k
- 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 OpenAI-MRCR: 2 needle 128k.
Which model scores highest on OpenAI-MRCR: 2 needle 128k?
GPT-5 is currently ranked first with 95.20%.
What are the top three models on OpenAI-MRCR: 2 needle 128k?
The current leaders are GPT-5 (95.20%), MiniMax M1 40K (76.10%), and MiniMax M1 80K (73.40%).
Which OpenAI-MRCR: 2 needle 128k model has the lowest official input price?
GPT-4.1 nano has the lowest matched official input price at $0.10 input / $0.40 output per 1M tokens.
Which models are fastest among OpenAI-MRCR: 2 needle 128k results?
The fastest matched records are GPT-4.1 mini (467.39 tok/s via OpenAI), GPT-4.1 nano (138.14 tok/s via OpenAI), and GPT-4o (132.00 tok/s via OpenAI).
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.