DeepSeek V3.2 (Non-reasoning)

deepseek-v3-2 · 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

36.5 34.5 #1 · 35.5 · 2026-05-11 23:17:33#2 · 35.5 · 2026-05-12 00:00:09#3 · 35.5 · 2026-05-12 01:00:09#4 · 35.5 · 2026-05-12 02:00:11

Cost over time

$198 $196 #1 · $197 · 2026-05-11 23:17:33#2 · $197 · 2026-05-12 00:00:09#3 · $197 · 2026-05-12 01:00:09#4 · $197 · 2026-05-12 02:00:11
Run?Fetched?Score?Quality?Cost?Intel?Code?Agent?MMMU%?
#4 2026-05-12 02:00:11 35.5 35.5 $197 32.1 34.6 39.8 -
#3 2026-05-12 01:00:09 35.5 35.5 $197 32.1 34.6 39.8 -
#2 2026-05-12 00:00:09 35.5 35.5 $197 32.1 34.6 39.8 -
#1 2026-05-11 23:17:33 35.5 35.5 $197 32.1 34.6 39.8 -