DeepSeek V4 Pro (Reasoning, Max Effort)

deepseek-v4-pro · 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

56.4 54.4 #1 · 55.4 · 2026-05-11 23:17:33#2 · 55.4 · 2026-05-12 00:00:09#3 · 55.4 · 2026-05-12 01:00:09#4 · 55.4 · 2026-05-12 02:00:11

Cost over time

$1,071 $1,071 #1 · $1,071 · 2026-05-11 23:17:33#2 · $1,071 · 2026-05-12 00:00:09#3 · $1,071 · 2026-05-12 01:00:09#4 · $1,071 · 2026-05-12 02:00:11
Run?Fetched?Score?Quality?Cost?Intel?Code?Agent?MMMU%?
#4 2026-05-12 02:00:11 55.4 55.4 $1,071 51.5 47.5 67.2 -
#3 2026-05-12 01:00:09 55.4 55.4 $1,071 51.5 47.5 67.2 -
#2 2026-05-12 00:00:09 55.4 55.4 $1,071 51.5 47.5 67.2 -
#1 2026-05-11 23:17:33 55.4 55.4 $1,071 51.5 47.5 67.2 -