DeepSeek V3.1 Terminus (Reasoning)

deepseek-v3-1-terminus-reasoning · 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

33.5 31.5 #1 · 32.5 · 2026-05-11 23:17:33#2 · 32.5 · 2026-05-12 00:00:09#3 · 32.5 · 2026-05-12 01:00:09#4 · 32.5 · 2026-05-12 02:00:11

Cost over time

$279 $277 #1 · $278 · 2026-05-11 23:17:33#2 · $278 · 2026-05-12 00:00:09#3 · $278 · 2026-05-12 01:00:09#4 · $278 · 2026-05-12 02:00:11
Run?Fetched?Score?Quality?Cost?Intel?Code?Agent?MMMU%?
#4 2026-05-12 02:00:11 32.5 32.5 $278 33.9 33.7 29.8 -
#3 2026-05-12 01:00:09 32.5 32.5 $278 33.9 33.7 29.8 -
#2 2026-05-12 00:00:09 32.5 32.5 $278 33.9 33.7 29.8 -
#1 2026-05-11 23:17:33 32.5 32.5 $278 33.9 33.7 29.8 -