Skip to content
llmwaves

V3.2

DeepSeek · released Dec 1, 2025

Open weightsReasoningTool useStructured output

DeepSeek-V3.2 is a large language model designed to harmonize high computational efficiency with strong reasoning and agentic tool-use performance. It introduces DeepSeek Sparse Attention (DSA), a fine-grained sparse attention mechanism...

Specification

Context window
164K
Max output
66K
Knowledge cutoff
Not stated
Parameters
685.4B
Licence
mit
Serving providers
14
Moderated
No
Uptime
100.0%

Intelligence

25.1

68th percentile

Coding

Coding Index

Agentic

Agentic Index

Output speed

100 t/s

Median across providers

Latency

676ms

Time to first token

Cost per task

$0.05

Estimated

Benchmarks

Where the score comes from

The Intelligence Index is a composite. These are the underlying evaluations this model was actually measured on.

Evaluation scores

Percentage correct · higher is better

  • MMLU-Pro
    83.7%
  • τ²-bench (Telecom)
    78.9%
  • GPQA Diamond
    75.1%
  • LiveCodeBench
    59.3%
  • AIME 2025
    59.0%
  • IFBench
    49.0%
  • AA-LCR (long context)
    42.7%
  • SciCode
    38.7%
  • Terminal-Bench Hard
    32.6%
  • Humanity's Last Exam
    11.2%

An evaluation missing from this list was not run for this model — it is not a zero.

View as table
EvaluationScore
MMLU-Pro83.7%
τ²-bench (Telecom)78.9%
GPQA Diamond75.1%
LiveCodeBench59.3%
AIME 202559.0%
IFBench49.0%
AA-LCR (long context)42.7%
SciCode38.7%
Terminal-Bench Hard32.6%
Humanity's Last Exam11.2%

Against its peers

Intelligence Index · this model highlighted, nearest peers in grey

Peers are the models sitting closest on the Intelligence Index — the set you would realistically choose between.

View as table
ModelIntelligence
Claude Opus 426.0
Gemini 2.5 Pro25.9
GPT-5 Mini25.8
Gemini 3.1 Flash Lite25.6
Gemini 3.1 Flash Lite Preview25.6
V3.225.1
Qwen3 Max24.5
Ling 3.0 Tiny (free)24.3

Percentile among all indexed models

Intelligence68th
Mathematics56th
Terminal work76th

Pricing

What it costs to run

List prices per million tokens, plus what one representative task works out to.

List price

Input / 1M tokens
$0.269
Output / 1M tokens
$0.4
Cached input / 1M
$0.135
Blended 3:1
$0.302

One task, estimated

$0.05

Input tokens
50,000
Output tokens
80,000
Profile
Reasoning

Estimated from list pricing: 50K input tokens plus 80K output tokens for reasoning models (25K for non-reasoning).

Serving providers

Speed and latency figures are medians across these providers, so a widely-served model reports a blend rather than any single endpoint.