DeepSeek V4 Flash (Reasoning, Max Effort)

deepseek-v4-flash · 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

49.8 47.8 #1 · 48.8 · 2026-05-11 23:17:33#2 · 48.8 · 2026-05-12 00:00:09#3 · 48.8 · 2026-05-12 01:00:09

Cost over time

$114 $112 #1 · $113 · 2026-05-11 23:17:33#2 · $113 · 2026-05-12 00:00:09#3 · $113 · 2026-05-12 01:00:09
Run?Fetched?Score?Quality?Cost?Intel?Code?Agent?MMMU%?
#3 2026-05-12 01:00:09 48.8 48.8 $113 46.5 38.7 61.3 -
#2 2026-05-12 00:00:09 48.8 48.8 $113 46.5 38.7 61.3 -
#1 2026-05-11 23:17:33 48.8 48.8 $113 46.5 38.7 61.3 -