GPT-5 mini (medium)

gpt-5-mini-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

38.6 36.6 #1 · 37.6 · 2026-05-11 23:17:33#2 · 37.6 · 2026-05-12 00:00:09#3 · 37.6 · 2026-05-12 01:00:09#4 · 37.6 · 2026-05-12 02:00:11

Cost over time

$62.9 $60.9 #1 · $61.9 · 2026-05-11 23:17:33#2 · $61.9 · 2026-05-12 00:00:09#3 · $61.9 · 2026-05-12 01:00:09#4 · $61.9 · 2026-05-12 02:00:11
Run?Fetched?Score?Quality?Cost?Intel?Code?Agent?MMMU%?
#4 2026-05-12 02:00:11 37.6 37.6 $61.9 38.9 32.9 40.9 68.8
#3 2026-05-12 01:00:09 37.6 37.6 $61.9 38.9 32.9 40.9 68.8
#2 2026-05-12 00:00:09 37.6 37.6 $61.9 38.9 32.9 40.9 68.8
#1 2026-05-11 23:17:33 37.6 37.6 $61.9 38.9 32.9 40.9 68.8