MMODELYST
Models/DeepSeek V3.2
MDL

DeepSeek V3.2

DeepSeek

Verified against Artificial Analysis · Jul 13, 2026
Capability
87
percentile index
Price /M
$0.28 / $0.42
in / out
Context
131.1K
tokens
Avg score
66.1
10 benchmarks
AA Intelligence
32.0
index
Weights
Open
Released
Dec 1, 2025
About

DeepSeek V3.2 is a open-weights model in the DeepSeek family from DeepSeek. Benchmarked on 10 evals, averaging 66.1.

Benchmark scores · 10
avg 66.1 — higher is better
AIME
92
τ²-bench
90.6
MMLU-Pro
86.2
LiveCodeBench
86.2
GPQA Diamond
84
AA Long-Context Reasoning
65
IFBench
60.7
SciCode
38.9
Terminal-Bench Hard
35.6
Humanity's Last Exam
22.2
Details
PublisherDeepSeek
FamilyDeepSeek
Parameters
License
WeightsOpen
ReleasedDec 1, 2025
Performance & price
Price in / out$0.28 / $0.42 per 1M
Blended price$0.315 / 1M
Coding index44.2
Math index92.0

Median across API providers, via Artificial Analysis. Blended = 3:1 input:output. For reasoning models, latency includes thinking time. Methodology →

Capability over time

Append-only ledger — every observed change to this model's numbers.

API providers
Artificial Analysis$0.42/M