GPT-5.2 (xhigh)

gpt-5-2 · 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

54.4 52.4 #1 · 53.4 · 2026-05-11 23:17:33#2 · 53.4 · 2026-05-12 00:00:09#3 · 53.4 · 2026-05-12 01:00:09#4 · 53.4 · 2026-05-12 02:00:11

Cost over time

$2,305 $2,303 #1 · $2,304 · 2026-05-11 23:17:33#2 · $2,304 · 2026-05-12 00:00:09#3 · $2,304 · 2026-05-12 01:00:09#4 · $2,304 · 2026-05-12 02:00:11
Run?Fetched?Score?Quality?Cost?Intel?Code?Agent?MMMU%?
#4 2026-05-12 02:00:11 53.4 53.4 $2,304 51.3 48.7 60.2 -
#3 2026-05-12 01:00:09 53.4 53.4 $2,304 51.3 48.7 60.2 -
#2 2026-05-12 00:00:09 53.4 53.4 $2,304 51.3 48.7 60.2 -
#1 2026-05-11 23:17:33 53.4 53.4 $2,304 51.3 48.7 60.2 -