Thoughts on AI, technology, and the future we're building.

New posts every week

HomeAll PostsAI NewsAI Basics
Timelines
ChatGPTOpenAI release historyAnthropic ClaudeClaude release historyGoogle GeminiGemini release history
Benchmarks
OverviewFull model trackerValue RankingsPerformance for the moneyCoding RankingsSWE-bench and code signalsAgent RankingsTool and workflow signalsReasoning RankingsKnowledge and reasoningLong ContextDocument and retrieval signalsLab ComparisonsProvider-level rankings
CategoriesAboutContact

Subscribe to Newsletter

Practical AI news, tips, tricks, tool analysis, sent straight to your inbox.

No spam. Unsubscribe anytime.

Practical explainers, tool notes, and systems thinking for people turning new AI capability into useful work.

Explore

  • All Posts
  • Categories
  • About
  • Contact

Categories

  • AI News
  • AI Basics
  • ChatGPT
  • Anthropic
  • AI Tools
  • AI Video
  • AI Images
  • Courses

Connect

LinkedInTwitterRSS

© 2026. All rights reserved.

Benchmark suiteUpdated May 27, 2026

DeepSeek benchmarks.

A lab-level profile for DeepSeek, covering tracked models, category leaders, open/proprietary mix, speed, value, source coverage, and portfolio depth.

All labs

Lab rank

#17

By available Arena average

Models tracked

13

13 open-weight models

Portfolio coverage

28%

Average matched benchmark signals

Fastest model

0.96s

DeepSeek V4 Flash

OverviewFull public trackerValuePerformance for the moneyCodingCode and SWE-bench signalsAgentsTool and workflow readinessReasoningKnowledge and reasoning signalsContextDocument and retrieval signalsLabsProvider comparisons

Lab profile

Portfolio shape, leaders, and model coverage.

The lab page now starts with the portfolio read, then drills into category leaders, value rankings, and model-level coverage rather than repeating source panels.

Portfolio read

DeepSeek has 13 tracked benchmark profiles.

Lab #17

The portfolio combines 0 proprietary models and 13 open-weight models. Its average available Arena rank is 65.3, with a best category rank of #17. Average profile coverage is 28%, so model-level gaps remain visible in the cards below.

Best Arena model

DeepSeek V4 Pro Thinking

Best category rank #17

Highest coverage

DeepSeek V4 Pro Thinking

56% matched signals

Fastest response

DeepSeek V4 Flash

0.96s first token

Access mix

Open versus proprietary

Proprietary

0 / 0%

Open weights

13 / 100%

Value leader

DeepSeek V4 Pro Thinking

Category leaders

Best model by benchmark lens.

Each card shows the highest-ranked model from this lab in a composite benchmark suite, with the global rank and index left intact.

Value

Quality, price, latency, and speed

DeepSeek V4 Pro Thinking

#1871

value index

Coding

Code Arena, SWE-bench, and output speed

DeepSeek V3.2

#2567

coding index

Agents

Search, document, code, and latency

DeepSeek V4 Flash

#7100

agent proxy

Reasoning

Text, document, vision, and mode signals

DeepSeek V4 Pro Thinking

#4552

reasoning proxy

Context

Document, search, and text proxy

DeepSeek V4 Pro Thinking

#4952

context proxy

DeepSeek value ranking table

Models from this lab with both quality and commercial price matches.

Top 9 of 9

RankModelIndexPriceLatencySpeedQualitySources
#18
DeepSeek V4 Pro Thinking

deepseek-v4-pro-thinking

DeepSeekOpen weights
71value index
$0.544blended / 1M tokens
1.11stime to first token
44 tok/soutput speed
64quality signal
ArenaArtificial Analysis
#37
DeepSeek V4 Pro

deepseek-v4-pro

DeepSeekOpen weights
62value index
$0.544blended / 1M tokens
1.15stime to first token
43 tok/soutput speed
47quality signal
ArenaArtificial Analysis
#61
DeepSeek V3.2

deepseek-v3.2

DeepSeekOpen weights
54value index
$0.775blended / 1M tokens
Not listedtime to first token
Not listedoutput speed
31quality signal
ArenaArtificial Analysis
#64
DeepSeek V4 Flash Thinking

deepseek-v4-flash-thinking

DeepSeekOpen weights
53value index
$0.175blended / 1M tokens
Not listedtime to first token
Not listedoutput speed
29quality signal
ArenaArtificial Analysis
#68
DeepSeek V4 Flash

deepseek-v4-flash

DeepSeekOpen weights
52value index
$0.175blended / 1M tokens
0.96stime to first token
109 tok/soutput speed
24quality signal
ArenaArtificial Analysis
#69
DeepSeek V3.2 Exp

deepseek-v3.2-exp

DeepSeekOpen weights
52value index
$0.310blended / 1M tokens
Not listedtime to first token
Not listedoutput speed
26quality signal
ArenaArtificial Analysis
#81
DeepSeek R1 0528

deepseek-r1-0528

DeepSeekOpen weights
41value index
$2.06blended / 1M tokens
Not listedtime to first token
Not listedoutput speed
12quality signal
ArenaArtificial Analysis
#82
DeepSeek V3.1

deepseek-v3.1

DeepSeekOpen weights
39value index
$0.865blended / 1M tokens
Not listedtime to first token
Not listedoutput speed
8quality signal
ArenaArtificial Analysis
#85
DeepSeek V3.1 Terminus

deepseek-v3.1-terminus

DeepSeekOpen weights
37value index
$1.91blended / 1M tokens
Not listedtime to first token
Not listedoutput speed
5quality signal
ArenaArtificial Analysis
#18
DeepSeek V4 Pro Thinking

deepseek-v4-pro-thinking

DeepSeekOpen weights
71value index
Price
$0.544blended / 1M tokens
Latency
1.11stime to first token
Speed
44 tok/soutput speed
Quality
64quality signal
ArenaArtificial Analysis
#37
DeepSeek V4 Pro

deepseek-v4-pro

DeepSeekOpen weights
62value index
Price
$0.544blended / 1M tokens
Latency
1.15stime to first token
Speed
43 tok/soutput speed
Quality
47quality signal
ArenaArtificial Analysis
#61
DeepSeek V3.2

deepseek-v3.2

DeepSeekOpen weights
54value index
Price
$0.775blended / 1M tokens
Latency
Not listedtime to first token
Speed
Not listedoutput speed
Quality
31quality signal
ArenaArtificial Analysis
#64
DeepSeek V4 Flash Thinking

deepseek-v4-flash-thinking

DeepSeekOpen weights
53value index
Price
$0.175blended / 1M tokens
Latency
Not listedtime to first token
Speed
Not listedoutput speed
Quality
29quality signal
ArenaArtificial Analysis
#68
DeepSeek V4 Flash

deepseek-v4-flash

DeepSeekOpen weights
52value index
Price
$0.175blended / 1M tokens
Latency
0.96stime to first token
Speed
109 tok/soutput speed
Quality
24quality signal
ArenaArtificial Analysis
#69
DeepSeek V3.2 Exp

deepseek-v3.2-exp

DeepSeekOpen weights
52value index
Price
$0.310blended / 1M tokens
Latency
Not listedtime to first token
Speed
Not listedoutput speed
Quality
26quality signal
ArenaArtificial Analysis
#81
DeepSeek R1 0528

deepseek-r1-0528

DeepSeekOpen weights
41value index
Price
$2.06blended / 1M tokens
Latency
Not listedtime to first token
Speed
Not listedoutput speed
Quality
12quality signal
ArenaArtificial Analysis
#82
DeepSeek V3.1

deepseek-v3.1

DeepSeekOpen weights
39value index
Price
$0.865blended / 1M tokens
Latency
Not listedtime to first token
Speed
Not listedoutput speed
Quality
8quality signal
ArenaArtificial Analysis
#85
DeepSeek V3.1 Terminus

deepseek-v3.1-terminus

DeepSeekOpen weights
37value index
Price
$1.91blended / 1M tokens
Latency
Not listedtime to first token
Speed
Not listedoutput speed
Quality
5quality signal
ArenaArtificial Analysis

Model portfolio

DeepSeek model coverage map.

Every tracked model keeps its best Arena rank, coverage score, commercial metrics, and suite placement visible in one scannable grid.

DeepSeek V4 Pro Thinking

deepseek-v4-pro-thinking

Open weights

Coverage

56%

Best Arena

#17

Code

Value

#18

value index

Coding

#29

coding index

Latency

1.11s

44 tok/s

$0.544

DeepSeek V4 Pro

deepseek-v4-pro

Open weights

Coverage

44%

Best Arena

#38

Text

Value

#37

value index

Coding

#98

coding index

Latency

1.15s

43 tok/s

$0.544

DeepSeek V3.2 Thinking

deepseek-v3.2-thinking

Open weights

Coverage

22%

Best Arena

#49

Code

Value

Not listed

No price match

Coding

#42

coding index

Latency

Not listed

Not listed

Not listed

DeepSeek V3.2

deepseek-v3.2

Open weights

Coverage

44%

Best Arena

#58

Code

Value

#61

value index

Coding

#25

coding index

Latency

Not listed

Not listed

$0.775SWE #15

DeepSeek V4 Flash Thinking

deepseek-v4-flash-thinking

Open weights

Coverage

22%

Best Arena

#58

Text

Value

#64

value index

Coding

Not listed

No coding index

Latency

Not listed

Not listed

$0.175

DeepSeek V3.2 Exp

deepseek-v3.2-exp

Open weights

Coverage

33%

Best Arena

#64

Code

Value

#69

value index

Coding

#65

coding index

Latency

Not listed

Not listed

$0.310

DeepSeek V4 Flash

deepseek-v4-flash

Open weights

Coverage

44%

Best Arena

#65

Text

Value

#68

value index

Coding

#85

coding index

Latency

0.96s

109 tok/s

$0.175

DeepSeek V3.2 Exp Thinking

deepseek-v3.2-exp-thinking

Open weights

Coverage

11%

Best Arena

#73

Text

Value

Not listed

No price match

Coding

Not listed

No coding index

Latency

Not listed

Not listed

Not listed

DeepSeek R1 0528

deepseek-r1-0528

Open weights

Coverage

22%

Best Arena

#79

Text

Value

#81

value index

Coding

Not listed

No coding index

Latency

Not listed

Not listed

$2.06

DeepSeek V3.1

deepseek-v3.1

Open weights

Coverage

22%

Best Arena

#84

Text

Value

#82

value index

Coding

Not listed

No coding index

Latency

Not listed

Not listed

$0.865

DeepSeek V3.1 Terminus Thinking

deepseek-v3.1-terminus-thinking

Open weights

Coverage

11%

Best Arena

#85

Text

Value

Not listed

No price match

Coding

Not listed

No coding index

Latency

Not listed

Not listed

Not listed

DeepSeek V3.1 Thinking

deepseek-v3.1-thinking

Open weights

Coverage

11%

Best Arena

#88

Text

Value

Not listed

No price match

Coding

Not listed

No coding index

Latency

Not listed

Not listed

Not listed

DeepSeek V3.1 Terminus

deepseek-v3.1-terminus

Open weights

Coverage

22%

Best Arena

#89

Text

Value

#85

value index

Coding

Not listed

No coding index

Latency

Not listed

Not listed

$1.91