GPT-5.2 (Non-reasoning)

gpt-5-2-non-reasoning · 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

36.9 34.9 #1 · 35.9 · 2026-05-11 23:17:33#2 · 35.9 · 2026-05-12 00:00:09#3 · 35.9 · 2026-05-12 01:00:09#4 · 35.9 · 2026-05-12 02:00:11

Cost over time

$226 $224 #1 · $225 · 2026-05-11 23:17:33#2 · $225 · 2026-05-12 00:00:09#3 · $225 · 2026-05-12 01:00:09#4 · $225 · 2026-05-12 02:00:11
Run?Fetched?Score?Quality?Cost?Intel?Code?Agent?MMMU%?
#4 2026-05-12 02:00:11 35.9 35.9 $225 33.6 34.7 39.5 65.8
#3 2026-05-12 01:00:09 35.9 35.9 $225 33.6 34.7 39.5 65.8
#2 2026-05-12 00:00:09 35.9 35.9 $225 33.6 34.7 39.5 65.8
#1 2026-05-11 23:17:33 35.9 35.9 $225 33.6 34.7 39.5 65.8