GPT-5.3 Codex (xhigh)

gpt-5-3-codex · 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

56.7 54.7 #1 · 55.7 · 2026-05-11 23:17:33#2 · 55.7 · 2026-05-12 00:00:09#3 · 55.7 · 2026-05-12 01:00:09#4 · 55.7 · 2026-05-12 02:00:11

Cost over time

$1,573 $1,571 #1 · $1,572 · 2026-05-11 23:17:33#2 · $1,572 · 2026-05-12 00:00:09#3 · $1,572 · 2026-05-12 01:00:09#4 · $1,572 · 2026-05-12 02:00:11
Run?Fetched?Score?Quality?Cost?Intel?Code?Agent?MMMU%?
#4 2026-05-12 02:00:11 55.7 55.7 $1,572 53.6 53.1 60.5 78.5
#3 2026-05-12 01:00:09 55.7 55.7 $1,572 53.6 53.1 60.5 78.5
#2 2026-05-12 00:00:09 55.7 55.7 $1,572 53.6 53.1 60.5 78.5
#1 2026-05-11 23:17:33 55.7 55.7 $1,572 53.6 53.1 60.5 78.5