Translate
Independent model intelligence

Find the right AI model,
not just the loudest one.

Compare current model capability, context, modalities, public preference and API economics in one continuously refreshed decision surface.

LMArena models.dev OpenRouter Artificial Analysis when available
Back to leaderboard
DeepSeek · Active

deepseek-v3.1-terminus

deepseek family · launched 2025-08-02

ReasoningToolsStructuredOpen weights
AITopic score46.2#49 overall

DeepSeek chat model for instruction following, coding, and analysis

Evidence coverage3%1 evaluations · 1 institutions
Context / maximum output128k / 65.5ktokens
Cache / input / output$0.13 · $0.25 · $0.7USD per million tokens
Value / freshness61.2 / 40relative value · release freshness
Product profile

What this model supports

Inputtext
Outputtext
Knowledge cutoff2025-03-31
WeightsOpen weights
Capability profile

Strengths by domain

Coding—0 public results
Research & reasoning—0 public results
Professional work—0 public results
Knowledge & instruction—0 public results
Behind the score

Every result has a source

Raw results and standardized readings are shown together. Missing tests add neither points nor penalties.

Human preference & indices2 results

AA IndexArtificial Analysis61.77 indexReading 46.2

Imported from a directly fetched third-party leaderboard.

Configuration: deepseek-v3.1-terminusOpen evidence
Arena TextLMArena1,417.1 EloReading 46.2

Direct LMArena text leaderboard result.

Open evidence
Same builder

More from DeepSeek