DeepSeek: DeepSeek V3.1

deepseek/deepseek-chat-v3.1

Context: 163,840In: $0.25/1MOut: $0.95/1MUpdated 2026-08-05

DeepSeek-V3.1 is a large hybrid reasoning model (671B parameters, 37B active) that supports both thinking and non-thinking modes via prompt templates. It extends the DeepSeek-V3 base with a two-phase long-context...

Intelligence
Coding
Agentic

Metric profile

Trend over time

Intelligence
Coding
Agentic

Only 1 snapshot so far (data refreshes daily) — the trend line appears after the 2nd snapshot.

Classic evals (curated from model cards)

DeepSeek — manually maintained, may lag releases

MMLU-Pro
75%
GPQA Diamond
67%
MATH-500
95%

Design Arena (ELO by category)

CategoryELOWin rateRank
website114648%
#77
codecategories114147.9%
#77
3d113348%
#72
gamedev112947.1%
#74
dataviz112646.8%
#76
uicomponent112047.6%
#74
svg101438.2%
#75