GPT-5 Codex (high)

gpt-5-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

46.4 44.4 #1 · 45.4 · 2026-05-11 23:17:33#2 · 45.4 · 2026-05-12 00:00:09#3 · 45.4 · 2026-05-12 01:00:09#4 · 45.4 · 2026-05-12 02:00:11

Cost over time

$996 $994 #1 · $995 · 2026-05-11 23:17:33#2 · $995 · 2026-05-12 00:00:09#3 · $995 · 2026-05-12 01:00:09#4 · $995 · 2026-05-12 02:00:11
Run?Fetched?Score?Quality?Cost?Intel?Code?Agent?MMMU%?
#4 2026-05-12 02:00:11 45.4 45.4 $995 44.6 38.9 52.7 73.8
#3 2026-05-12 01:00:09 45.4 45.4 $995 44.6 38.9 52.7 73.8
#2 2026-05-12 00:00:09 45.4 45.4 $995 44.6 38.9 52.7 73.8
#1 2026-05-11 23:17:33 45.4 45.4 $995 44.6 38.9 52.7 73.8