Home Model series GPT unsuffixed models GPT-5 GPT-5 · OpenAI MRCR · 2 needles; 128k context · Scores and configurations GPT-5 · OpenAI MRCR · 2 needles; 128k context · Scores and configurations GPT-5 record for OpenAI MRCR · 2 needles; 128k context. 1 score record for this release, including 1 exact value (may include historical records). Includes 1 source location.
Scores and evaluation conditions GPT-5 · OpenAI MRCR scores and configurations Metric and score Configuration and evaluation conditions Sources Accuracy 95.2% Reported 95.2% · Unit % Published 2025-08-07
GPT-5 (high) Settings API reasoning model; the developer release benchmark table labels high reasoning effort. Unknowns none recorded Tools Tool access not recorded Reasoning budget high Framework not recorded Protocol OpenAI-MRCR: 2 needles, 128k context Conditions API GPT-5; high reasoning effort. View this score in rankings
Benchmark versions and metrics Aliases OpenAI-MRCR 2 needle 128k
Accuracy · % · Higher is better