Home Model series GPT nano GPT-5.4 nano GPT-5.4 nano · OpenAI MRCR · v2, 256K context, 8 needles · Scores and configurations GPT-5.4 nano · OpenAI MRCR · v2, 256K context, 8 needles · Scores and configurations GPT-5.4 nano record for OpenAI MRCR · v2, 256K context, 8 needles. 1 score record for this release, including 1 exact value (may include historical records). Includes 1 source location.
Scores and evaluation conditions GPT-5.4 nano · OpenAI MRCR scores and configurations Metric and score Configuration and evaluation conditions Sources Mean Match Ratio 33.1 Reported 33.1% · Unit not specified Published 2026-03-17
GPT-5.4 nano (xhigh) Settings The official comparison table labels GPT-5.4 nano (xhigh). Unknowns none recorded Tools Tool access not recorded Reasoning budget xhigh Framework not recorded Protocol OpenAI MRCR v2, 8 needles, 128K–256K context bin; mean match ratio. Conditions GPT-5.4 nano (xhigh); evaluation conducted in a research environment. 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