DeepSeek V3.1 Terminus (Non-reasoning)

deepseek-v3-1-terminus · 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

30.7 28.7 #1 · 29.7 · 2026-05-11 23:17:33#2 · 29.7 · 2026-05-12 00:00:09#3 · 29.7 · 2026-05-12 01:00:09#4 · 29.7 · 2026-05-12 02:00:11

Cost over time

$41.9 $39.9 #1 · $40.9 · 2026-05-11 23:17:33#2 · $40.9 · 2026-05-12 00:00:09#3 · $40.9 · 2026-05-12 01:00:09#4 · $40.9 · 2026-05-12 02:00:11
Run?Fetched?Score?Quality?Cost?Intel?Code?Agent?MMMU%?
#4 2026-05-12 02:00:11 29.7 29.7 $40.9 28.5 31.9 28.6 -
#3 2026-05-12 01:00:09 29.7 29.7 $40.9 28.5 31.9 28.6 -
#2 2026-05-12 00:00:09 29.7 29.7 $40.9 28.5 31.9 28.6 -
#1 2026-05-11 23:17:33 29.7 29.7 $40.9 28.5 31.9 28.6 -