Skip to content

DeepSeek V3.1

DeepSeekOpen weightsNon-reasoningVerifiedReleased Aug 21, 2025Input: text
Compare with Grok 3 [Beta]Source scores ↗OpenRouter ↗
Overall score
40.8
Rank 139 of 222 · 24.2–57.3
Context window
128K
128,000 tokens
Price per 1M tokens
$0.25 in · $0.95 out
Source: OpenRouter
Blended price
$0.42
3:1 input:output tokens
Output speed
—
Not measured yet

Category scores

Scores per capability area with the model's rank among ranked models in that category.

  1. 1Knowledge69.4
  2. 2Reasoning57.3
  3. 3Instruction following#11143.5
  4. 4Coding32.5
Higher is better. #N is the model's rank in that category, where it is eligible to be ranked.

Benchmark results (7)

As reported in system cards, papers and public evaluations. Position compares this model with every other model reporting the same benchmark.

Coding

SWE-bench Verified66.0#69 of 98
LiveCodeBench56.4#7 of 10

Knowledge

GPQA74.9#72 of 117
MMLU-Pro83.7#26 of 67

Math

AIME 202549.8#29 of 38
AIME 202466.3#13 of 19

Multimodal

Design Arena Website1124#76 of 91

Pricing by source

USD per 1M tokens.

SourceInputOutputCached in
List price (OpenRouter)$0.25$0.95—
OpenRouter deepseek/deepseek-chat-v3.1$0.25$0.95$0.13

Open-weight model. Self-hosted or third-party hosted costs vary by provider and infrastructure.

Arena ratings

Human-preference ratings from LMArena. Best-rated variant shown.

Text1420#116 · 14.6K votes

Open weights

From the Hugging Face repository.

Parameters
685B
Licence
mit
Downloads (30 days)
332.5K

Speed

Measured by us through OpenRouter (median of trials).

Not measured yet.

Related models

Same family

Similar score