Skip to content

OpenAI MRCR v2 8-needle 64K-128K

MRCR v2 slice focused on long-context retrieval at 64K-128K lengths.

2 models

Higher is better.

  1. 1Gemini 3.7 FlashGoogle97.0
  2. 2GPT-5.5OpenAI83.1
Higher is better. Bar colour: blue proprietary, orange open weights, green other.

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.