Skip to content

OpenAI MRCR v2 8-needle 128K-256K

MRCR v2 slice focused on very long contexts at 128K-256K lengths.

2 models

Higher is better.

  1. 1GPT-5.5OpenAI87.5
  2. 2Claude Opus 4.7 (Adaptive)Anthropic59.2
Higher is better. Bar colour: blue proprietary, orange open weights, green other.

About this benchmark

Metric
Very-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.