GPT-5 nano (medium)

gpt-5-nano-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

22.8 20.8 #1 · 21.8 · 2026-05-11 23:17:33#2 · 21.8 · 2026-05-12 00:00:09#3 · 21.8 · 2026-05-12 01:00:09#4 · 21.8 · 2026-05-12 02:00:11

Cost over time

$26.9 $24.9 #1 · $25.9 · 2026-05-11 23:17:33#2 · $25.9 · 2026-05-12 00:00:09#3 · $25.9 · 2026-05-12 01:00:09#4 · $25.9 · 2026-05-12 02:00:11
Run?Fetched?Score?Quality?Cost?Intel?Code?Agent?MMMU%?
#4 2026-05-12 02:00:11 21.8 21.8 $25.9 25.9 22.9 16.8 58.2
#3 2026-05-12 01:00:09 21.8 21.8 $25.9 25.9 22.9 16.8 58.2
#2 2026-05-12 00:00:09 21.8 21.8 $25.9 25.9 22.9 16.8 58.2
#1 2026-05-11 23:17:33 21.8 21.8 $25.9 25.9 22.9 16.8 58.2