DeepSeek V4 Flash (Reasoning, High Effort)

deepseek-v4-flash-high · 3 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

48.5 46.5 #1 · 47.5 · 2026-05-11 23:17:33#2 · 47.5 · 2026-05-12 00:00:09#3 · 47.5 · 2026-05-12 01:00:09

Cost over time

$58.2 $56.2 #1 · $57.2 · 2026-05-11 23:17:33#2 · $57.2 · 2026-05-12 00:00:09#3 · $57.2 · 2026-05-12 01:00:09
Run?Fetched?Score?Quality?Cost?Intel?Code?Agent?MMMU%?
#3 2026-05-12 01:00:09 47.5 47.5 $57.2 44.9 39.8 57.8 -
#2 2026-05-12 00:00:09 47.5 47.5 $57.2 44.9 39.8 57.8 -
#1 2026-05-11 23:17:33 47.5 47.5 $57.2 44.9 39.8 57.8 -