OpenAI
GPT-5-mini
Status: provisional
Summary stats
95% confidence interval: 966.743 to 1041.459.
Current status
Why this row is not ranked yet
samples_total<60, samples_holdout<20, distinct_opponents<3, conservative_signal_not_separated_adjacent
Head-to-head results
vs GPT-OSS-20B
10-2-0
12 raw games
BT edge: 0.833 (0.552 to 0.953)
vs GPT-OSS-120B
5-7-0
12 raw games
BT edge: 0.417 (0.193 to 0.680)