OpenAI MRCR v2 8-needle 64K-128K
MRCR v2 slice focused on long-context retrieval at 64K-128K lengths.
2 models
Higher is better.
- 1Gemini 3.7 FlashGoogle97.0
- 2GPT-5.5OpenAI83.1
About this benchmark
- Metric
- Long-context retrieval
- Tasks
- 8-needle retrieval tasks
- Authors
- OpenAI (2026)
Scores are as reported by model developers or evaluators and may use different settings (for example reasoning effort or tools). Compare with care.