GPT-5.4 (low)

gpt-5-4-low · 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

51.6 49.6 #1 · 50.6 · 2026-05-11 23:17:33#2 · 50.6 · 2026-05-12 00:00:09#3 · 50.6 · 2026-05-12 01:00:09#4 · 50.6 · 2026-05-12 02:00:11

Cost over time

$387 $385 #1 · $386 · 2026-05-11 23:17:33#2 · $386 · 2026-05-12 00:00:09#3 · $386 · 2026-05-12 01:00:09#4 · $386 · 2026-05-12 02:00:11
Run?Fetched?Score?Quality?Cost?Intel?Code?Agent?MMMU%?
#4 2026-05-12 02:00:11 50.6 50.6 $386 47.9 45.6 58.2 78.0
#3 2026-05-12 01:00:09 50.6 50.6 $386 47.9 45.6 58.2 78.0
#2 2026-05-12 00:00:09 50.6 50.6 $386 47.9 45.6 58.2 78.0
#1 2026-05-11 23:17:33 50.6 50.6 $386 47.9 45.6 58.2 78.0