Benchmarks
Benchmarks

MRCR v2 8-needle (512K-1M)

Reasoningunit % · normalized over [0, 100]

OpenAI MRCR v2, 8-needle variant, 512K-1M token band — the harder long-context retrieval band, where scores separated sharply through 2026.

#ModelSourceScoreNormalized
Score distribution
4 tracked results across the normalization window
0100
Score vs. parameters
Open-weights models, log-x params
No open-weights models with disclosed parameter counts have a score here yet.