GPT-5.2 (medium)

gpt-5-2-medium · 4 samples · combined / raw

Scoring

Choose the quality benchmark and final score formula for this model.

Cost adjustment

Tune formulas that account for benchmark cost.

Score over time

49.6 47.6 #1 · 48.6 · 2026-05-11 23:17:33#2 · 48.6 · 2026-05-12 00:00:09#3 · 48.6 · 2026-05-12 01:00:09#4 · 48.6 · 2026-05-12 02:00:11

Cost over time

$701 $699 #1 · $700 · 2026-05-11 23:17:33#2 · $700 · 2026-05-12 00:00:09#3 · $700 · 2026-05-12 01:00:09#4 · $700 · 2026-05-12 02:00:11
Run?Fetched?Score?Quality?Cost?Intel?Code?Agent?MMMU%?
#4 2026-05-12 02:00:11 48.6 48.6 $700 46.6 44.2 54.9 74.6
#3 2026-05-12 01:00:09 48.6 48.6 $700 46.6 44.2 54.9 74.6
#2 2026-05-12 00:00:09 48.6 48.6 $700 46.6 44.2 54.9 74.6
#1 2026-05-11 23:17:33 48.6 48.6 $700 46.6 44.2 54.9 74.6