GPT-5 nano (high)

gpt-5-nano · 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

24.4 22.4 #1 · 23.4 · 2026-05-11 23:17:33#2 · 23.4 · 2026-05-12 00:00:09#3 · 23.4 · 2026-05-12 01:00:09#4 · 23.4 · 2026-05-12 02:00:11

Cost over time

$52.7 $50.7 #1 · $51.7 · 2026-05-11 23:17:33#2 · $51.7 · 2026-05-12 00:00:09#3 · $51.7 · 2026-05-12 01:00:09#4 · $51.7 · 2026-05-12 02:00:11
Run?Fetched?Score?Quality?Cost?Intel?Code?Agent?MMMU%?
#4 2026-05-12 02:00:11 23.4 23.4 $51.7 26.8 20.3 23.3 61.0
#3 2026-05-12 01:00:09 23.4 23.4 $51.7 26.8 20.3 23.3 61.0
#2 2026-05-12 00:00:09 23.4 23.4 $51.7 26.8 20.3 23.3 61.0
#1 2026-05-11 23:17:33 23.4 23.4 $51.7 26.8 20.3 23.3 61.0