supermarket

Language

DeepSeek-V3.1-Terminus

By DeepSeek, in the DeepSeek-V family.

Released
22 Sep 2025
Status
Legacy
Context
131.1K
Max output
—
Input per 1M tokens
—
Output per 1M tokens
—
Open weights
Yes
License
mit
Parameters
671B, 37B active
Knowledge cutoff
—
Reasoning
Yes
Modalities
text → text

Category scores

Out of 100, from independent and third-party results only, by method category-2026-09-29.1.

Category scores
CategoryScoreRankCoverage
Knowledge & reasoning33.6Not ranked1 of 4
Human preference52.5Not ranked1 of 5

Benchmark results

Every result we hold for this model, with who ran it and where it was published.

Knowledge & reasoning

Knowledge & reasoning results
BenchmarkMetricValueProvenanceSettingEvaluatedSource
DTBench (Decision Theory Benchmark)Accuracy (capability questions)81.3%Third party——https://conceptualreasoning.ai/dtbench via Epoch AI
LMCA (Language Model Conceptual Argumentation)Correlation with expert ratings (Pearson r)0.2858Third party——https://conceptualreasoning.ai/lmca via Epoch AI

Human preference

Human preference results
BenchmarkMetricValueProvenanceSettingEvaluatedSource
Text Arena (arena.ai)Arena score (Elo scale)1417Independentthinking25 Sep 2026Arena
Text Arena (arena.ai)Arena score (Elo scale)1415Independent—25 Sep 2026Arena
Text Arena (arena.ai)Votes3600Independent—25 Sep 2026Arena
Text Arena (arena.ai)Votes3351Independentthinking25 Sep 2026Arena

Other DeepSeek-V versions

Sources