GPT-5 (medium)

gpt-5-medium · 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

43.3 41.3 #1 · 42.3 · 2026-05-11 23:17:33#2 · 42.3 · 2026-05-12 00:00:09#3 · 42.3 · 2026-05-12 01:00:09#4 · 42.3 · 2026-05-12 02:00:11

Cost over time

$551 $549 #1 · $550 · 2026-05-11 23:17:33#2 · $550 · 2026-05-12 00:00:09#3 · $550 · 2026-05-12 01:00:09#4 · $550 · 2026-05-12 02:00:11
Run?Fetched?Score?Quality?Cost?Intel?Code?Agent?MMMU%?
#4 2026-05-12 02:00:11 42.3 42.3 $550 42.0 39.0 45.8 74.3
#3 2026-05-12 01:00:09 42.3 42.3 $550 42.0 39.0 45.8 74.3
#2 2026-05-12 00:00:09 42.3 42.3 $550 42.0 39.0 45.8 74.3
#1 2026-05-11 23:17:33 42.3 42.3 $550 42.0 39.0 45.8 74.3