Magistral Small 1.2

magistral-small-2509 · 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

17.8 15.8 #1 · 16.8 · 2026-05-11 23:17:33#2 · 16.8 · 2026-05-12 00:00:09#3 · 16.8 · 2026-05-12 01:00:09#4 · 16.8 · 2026-05-12 02:00:11

Cost over time

$90.8 $88.8 #1 · $89.8 · 2026-05-11 23:17:33#2 · $89.8 · 2026-05-12 00:00:09#3 · $89.8 · 2026-05-12 01:00:09#4 · $89.8 · 2026-05-12 02:00:11
Run?Fetched?Score?Quality?Cost?Intel?Code?Agent?MMMU%?
#4 2026-05-12 02:00:11 16.8 16.8 $89.8 18.2 14.8 17.3 55.5
#3 2026-05-12 01:00:09 16.8 16.8 $89.8 18.2 14.8 17.3 55.5
#2 2026-05-12 00:00:09 16.8 16.8 $89.8 18.2 14.8 17.3 55.5
#1 2026-05-11 23:17:33 16.8 16.8 $89.8 18.2 14.8 17.3 55.5