GPT-5.2 Codex (xhigh)

gpt-5-2-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

50.5 48.5 #1 · 49.5 · 2026-05-11 23:17:33#2 · 49.5 · 2026-05-12 00:00:09#3 · 49.5 · 2026-05-12 01:00:09#4 · 49.5 · 2026-05-12 02:00:11

Cost over time

$3,245 $3,243 #1 · $3,244 · 2026-05-11 23:17:33#2 · $3,244 · 2026-05-12 00:00:09#3 · $3,244 · 2026-05-12 01:00:09#4 · $3,244 · 2026-05-12 02:00:11
Run?Fetched?Score?Quality?Cost?Intel?Code?Agent?MMMU%?
#4 2026-05-12 02:00:11 49.5 49.5 $3,244 49.0 43.0 56.5 76.3
#3 2026-05-12 01:00:09 49.5 49.5 $3,244 49.0 43.0 56.5 76.3
#2 2026-05-12 00:00:09 49.5 49.5 $3,244 49.0 43.0 56.5 76.3
#1 2026-05-11 23:17:33 49.5 49.5 $3,244 49.0 43.0 56.5 76.3