DeepSeek V3 (Dec '24)

deepseek-v3 · 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

14.9 12.9 #1 · 13.9 · 2026-05-11 23:17:33#2 · 13.9 · 2026-05-12 00:00:09#3 · 13.9 · 2026-05-12 01:00:09#4 · 13.9 · 2026-05-12 02:00:11

Cost over time

$27.8 $25.8 #1 · $26.8 · 2026-05-11 23:17:33#2 · $26.8 · 2026-05-12 00:00:09#3 · $26.8 · 2026-05-12 01:00:09#4 · $26.8 · 2026-05-12 02:00:11
Run?Fetched?Score?Quality?Cost?Intel?Code?Agent?MMMU%?
#4 2026-05-12 02:00:11 13.9 13.9 $26.8 16.5 16.4 8.8 -
#3 2026-05-12 01:00:09 13.9 13.9 $26.8 16.5 16.4 8.8 -
#2 2026-05-12 00:00:09 13.9 13.9 $26.8 16.5 16.4 8.8 -
#1 2026-05-11 23:17:33 13.9 13.9 $26.8 16.5 16.4 8.8 -