Benchmark suiteUpdated May 27, 2026

DeepSeek V3.2.

A model-level benchmark profile for DeepSeek V3.2, combining Arena category ranks, suite indexes, commercial price and speed data, SWE-bench status, and lab context.

DeepSeek lab page

Lab

DeepSeek

Open weights

Coverage

44%

4 of 9 tracked signals

Best Arena rank

#58

WebDev Arena

Best suite

#25

Coding / 67

Model profile

Benchmark signal map.

This view treats missing values as coverage gaps, then puts every available score, rank, cost, and speed signal into the same visual hierarchy.

Analyst view

DeepSeek V3.2 is strongest on coding.

44% coverage

Its best composite result is rank #25 in the coding view, with a 67 coding index. The strongest raw Arena signal is WebDev Arena at rank #58 with 10,463 public votes.

Best current lane

Coding

#25 / 67 coding index

Strongest raw signal

Code

#58, 1332 score

Commercial posture

$0.775

Not listed first token / Not listed

Coverage gaps

Vision ArenaSearch ArenaDocument ArenaLatencyOutput speed

Profile completeness

4 of 9 signals matched

44%

Arena categories

2/5

Code, Text

Commercial match

Live

DeepSeek V3.2 (Non-reasoning)

SWE-bench

#15

bash-only

Raw identifier

deepseek-v3.2

Open weights

Performance cockpit

Public benchmark scores

Arena rows show score, public rank, confidence interval, vote count, and publish date. Missing rows stay visible as coverage gaps.

Text Arena

Arena category

1,424#74

1421-1428 CI

46,204 votes

May 27, 2026

Arena public leaderboard dataset

WebDev Arena

Arena category

1,332#58

1325-1339 CI

10,463 votes

May 25, 2026

Arena public leaderboard dataset

Vision Arena

Arena category

Not listed

No confident public Arena row for this category.

Coverage gap

Search Arena

Arena category

Not listed

No confident public Arena row for this category.

Coverage gap

Document Arena

Arena category

Not listed

No confident public Arena row for this category.

Coverage gap

SWE-bench Verified

Software issue resolution

70%#15

bash-only

deepseek-v3.2

Feb 17, 2026

SWE-bench Verified

Cost and speed

Commercial profile

Price, latency, and throughput are only shown when a confident commercial source row is matched.

Blended price

$0.775

USD / 1M tokens

Input price

$0.500

USD / 1M input tokens

Output price

$1.60

USD / 1M output tokens

Latency

Not listed

Median time to first token

Output speed

Not listed

Median generation speed

Matched source row

DeepSeek V3.2 (Non-reasoning)

Suite position

Composite ranks by benchmark lens.

These views combine available public signals into purpose-specific indexes. A missing card means the model lacks enough source coverage for that lens.

Value

Quality, price, latency, and output speed

#6154

value index

blended / 1M tokens$0.775

time to first tokenNot listed

output speedNot listed

Coding

Code Arena, SWE-bench, and output speed

#2567

coding index

Code Arena rank #581,332