GPT-5.4 nano (medium)

gpt-5-4-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

39.3 37.3 #1 · 38.3 · 2026-05-11 23:17:33#2 · 38.3 · 2026-05-12 00:00:09#3 · 38.3 · 2026-05-12 01:00:09#4 · 38.3 · 2026-05-12 02:00:11

Cost over time

$92.0 $90.0 #1 · $91.0 · 2026-05-11 23:17:33#2 · $91.0 · 2026-05-12 00:00:09#3 · $91.0 · 2026-05-12 01:00:09#4 · $91.0 · 2026-05-12 02:00:11
Run?Fetched?Score?Quality?Cost?Intel?Code?Agent?MMMU%?
#4 2026-05-12 02:00:11 38.3 38.3 $91.0 38.1 35.0 41.6 59.5
#3 2026-05-12 01:00:09 38.3 38.3 $91.0 38.1 35.0 41.6 59.5
#2 2026-05-12 00:00:09 38.3 38.3 $91.0 38.1 35.0 41.6 59.5
#1 2026-05-11 23:17:33 38.3 38.3 $91.0 38.1 35.0 41.6 59.5