DeepSeek V3.2 Exp (Non-reasoning)

deepseek-v3-2-0925 · 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

30.8 28.8 #1 · 29.8 · 2026-05-11 23:17:33#2 · 29.8 · 2026-05-12 00:00:09#3 · 29.8 · 2026-05-12 01:00:09#4 · 29.8 · 2026-05-12 02:00:11

Cost over time

$47.9 $45.9 #1 · $46.9 · 2026-05-11 23:17:33#2 · $46.9 · 2026-05-12 00:00:09#3 · $46.9 · 2026-05-12 01:00:09#4 · $46.9 · 2026-05-12 02:00:11
Run?Fetched?Score?Quality?Cost?Intel?Code?Agent?MMMU%?
#4 2026-05-12 02:00:11 29.8 29.8 $46.9 28.4 30.0 31.0 -
#3 2026-05-12 01:00:09 29.8 29.8 $46.9 28.4 30.0 31.0 -
#2 2026-05-12 00:00:09 29.8 29.8 $46.9 28.4 30.0 31.0 -
#1 2026-05-11 23:17:33 29.8 29.8 $46.9 28.4 30.0 31.0 -