Home Model series Claude Sonnet Claude Sonnet 4.6 Claude Sonnet 4.6 · OpenAI MRCR · v2, 256K context, 8 needles · Scores and configurations Claude Sonnet 4.6 · OpenAI MRCR · v2, 256K context, 8 needles · Scores and configurations Claude Sonnet 4.6 record for OpenAI MRCR · v2, 256K context, 8 needles. 2 score records for this release, including 2 exact values (may include historical records). Includes 1 source location.
Scores and evaluation conditions Claude Sonnet 4.6 · OpenAI MRCR scores and configurations Metric and score Configuration and evaluation conditions Sources Mean Match Ratio 90.6 Reported 90.6 (64k) · Unit not specified Published Unconfirmed
64K extended thinking Settings Extended thinking with a 64K token budget. Unknowns Effort setting is not stated for the long-context table results. Tools Tool access not recorded Reasoning budget Thinking budget 64K Framework not recorded Protocol OpenAI MRCR v2, 256K context bin, 8 needles; Mean Match Ratio. Conditions Five-trial average; 1M context window; default sampling. Mean Match Ratio 90.3 Reported 90.3 (max) · Unit not specified Published Unconfirmed
Adaptive thinking, max effort Settings Adaptive thinking enabled; max effort; default temperature and top_p unless an evaluation specifies otherwise. Unknowns Context window is evaluation-dependent; Table 2.1.A states it does not exceed 1M tokens. Tools Tool access not recorded Reasoning budget max Framework not recorded Protocol OpenAI MRCR v2, 256K context bin, 8 needles; Mean Match Ratio. Conditions Five-trial average; 1M context window; default sampling. View this score in rankings
Benchmark versions and metrics Aliases OpenAI MRCR v2 256K 8-needles
Mean Match Ratio · Unit not specified · Higher is better