DeepSeek V4 Flash (Non-reasoning)

deepseek-v4-flash-non-reasoning · 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

45.3 43.3 #1 · 44.3 · 2026-05-11 23:17:33#2 · 44.3 · 2026-05-12 00:00:09#3 · 44.3 · 2026-05-12 01:00:09

Cost over time

$41.0 $39.0 #1 · $40.0 · 2026-05-11 23:17:33#2 · $40.0 · 2026-05-12 00:00:09#3 · $40.0 · 2026-05-12 01:00:09
Run?Fetched?Score?Quality?Cost?Intel?Code?Agent?MMMU%?
#3 2026-05-12 01:00:09 44.3 44.3 $40.0 36.5 35.1 61.3 -
#2 2026-05-12 00:00:09 44.3 44.3 $40.0 36.5 35.1 61.3 -
#1 2026-05-11 23:17:33 44.3 44.3 $40.0 36.5 35.1 61.3 -