Benchmark

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

MRCR v2 8-needle variant evaluated on contexts from 512K to 1M tokens.

Modality
text
Categories
long_context, reasoning, general
Openness
unknown
Source
llm_stats
Reported scores
3

Reported scores

llm_stats

ModelOrganizationReported valueReportedEvidence
GPT-5.6 LunaOpenAI0.4132026-07-09evidence
GPT-5.6 SolOpenAI0.7382026-07-09evidence
GPT-5.6 TerraOpenAI0.7252026-07-09evidence

Scores are partitioned by the source that reported them and are never merged into a single cross-source ranking, because the sources measure different things and say so.