GPT-5.4 (Non-reasoning)

gpt-5-4-non-reasoning · 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

39.5 37.5 #1 · 38.5 · 2026-05-11 23:17:33#2 · 38.5 · 2026-05-12 00:00:09#3 · 38.5 · 2026-05-12 01:00:09#4 · 38.5 · 2026-05-12 02:00:11

Cost over time

$273 $271 #1 · $272 · 2026-05-11 23:17:33#2 · $272 · 2026-05-12 00:00:09#3 · $272 · 2026-05-12 01:00:09#4 · $272 · 2026-05-12 02:00:11
Run?Fetched?Score?Quality?Cost?Intel?Code?Agent?MMMU%?
#4 2026-05-12 02:00:11 38.5 38.5 $272 35.4 41.0 39.1 70.6
#3 2026-05-12 01:00:09 38.5 38.5 $272 35.4 41.0 39.1 70.6
#2 2026-05-12 00:00:09 38.5 38.5 $272 35.4 41.0 39.1 70.6
#1 2026-05-11 23:17:33 38.5 38.5 $272 35.4 41.0 39.1 70.6