Skip to main content

OpenAIDeepSeekLLM matchup

GPT-5.4vs.DeepSeek-V4-Pro

Which one is better?

GPT-5.4 and DeepSeek-V4-Pro perform about equally well, but GPT-5.4 costs 3.8 times (input) and 7.6 times (output) as much.

level
IntelligenceOverall index, 100 points = average
86.4

GPT-5.4

Rank 50

87.1

DeepSeek-V4-Pro

Rank 48

GPT-5.4 faster
SpeedTokens per second
64

GPT-5.4

42

DeepSeek-V4-Pro

DeepSeek-V4-Pro cheaper
Price$ per 1M tokens
$5.63

GPT-5.4

$0.99

DeepSeek-V4-Pro

Popularity0 to 100
n/a

GPT-5.4

75

DeepSeek-V4-Pro

Rank 26 of 508

Above 272,000 tokens of context, GPT-5.4 costs more: $5 input and $22.50 output per 1M tokens.

Choose GPT-5.4 for

Reasoning (not certain)

Choose DeepSeek-V4-Pro for

Coding (not certain)Agents (not certain)

Where is the difference?

Strengths at a glance

GPT-5.4DeepSeek-V4-ProMedian of all ranked models

809010070CodingslightlyDeepSeek-V4-ProReasoningslightlyGPT-5.4AgentsslightlyDeepSeek-V4-ProFinancelevelLegallevelHealthlevel
CodingDeepSeek-V4-Pro slightly ahead
GPT-5.485.0Rank 60
DeepSeek-V4-Pro91.1Rank 53
Median of ranked models87.5

95 % range: GPT-5.4 75.3 to 94.6, DeepSeek-V4-Pro 85.2 to 96.9.

AreaGPT-5.4DeepSeek-V4-Pro

The same values and verdicts as the bars below. In the close-up the net starts at 70 points, just below the weaker model's lowest value; the reference group average is 100. Not in the net because a model has no own value there or the data are too thin: Mathematics, Knowledge, General, Multimodal.

Neither model is clearly ahead in any of the 10 areas.

GPT-5.4 slightly ahead: 1level: 3too little data: 4DeepSeek-V4-Pro slightly ahead: 2

Areas in the overall index
Codingleaning DeepSeek-V4-Pronot certain · 6 and 10 tests
Reasoningleaning GPT-5.4not certain · 3 and 5 tests
Agentsleaning DeepSeek-V4-Pronot certain · 3 and 4 tests
Knowledgetoo little data87.0 to 89.1
Generaltoo little data86.1 to 87.6
Mathematicsonly DeepSeek-V4-Pro has a score
Multimodalonly GPT-5.4 has a score
Specialist fields
Financelevel85.9 to 87.4
Healthlevel80.4 to 79.4
Legallevel83.9 to 83.1

Bar length shows the gap in index points (full width 15 points, one standard deviation of the reference group). Solid means clearly ahead, hatched not certain yet, a thin grey bar level.

Show 1 more areas that do not count toward the overall index
Productivityonly DeepSeek-V4-Pro has a score

Bar length shows the gap in index points (full width 15 points, one standard deviation of the reference group). Solid means clearly ahead, hatched not certain yet, a thin grey bar level.

Which model for which task?

Everyday tasks, translated from the area values above. Each row names the values it rests on.

Writing and debugging codeleaning DeepSeek-V4-ProCoding 85.0 to 91.1
Maths and data analysisleaning GPT-5.4Mathematics without a score for GPT-5.4, Reasoning 87.9 to 84.1
Facts and researchopenKnowledge 87.0 to 89.1 (too little data)
Agents and workflowsleaning DeepSeek-V4-ProAgents 90.5 to 93.9
Fast chat repliesGPT-5.464 to 42 tokens per second
Many requests on a small budgetDeepSeek-V4-Pro$5.63 to $0.99 per 1M tokens
Finance, legal and medical textslevelFinance 85.9 to 87.4, Legal 83.9 to 83.1, Health 80.4 to 79.4
Images, screenshots and PDFsopenMultimodal without a score for DeepSeek-V4-Pro

GPT-5.4 vs. DeepSeek-V4-Pro in our own test

The same prompt for both models. We show the latest attempt without fixes; it does not count toward the overall index.

Pelican on a bicycle

Prompt

Generate an SVG of a pelican riding a bicycle

Task origin: Simon Willison

GPT-5.4

GPT-5.4: Pelican on a bicycle
A community classic for free-form SVG drawing.

Oct 1, 2026 · 117 s · $0.11

Test details
Run date
Oct 1, 2026
API provider
openrouter
Requested API model
openai/gpt-5.4
Reasoning setting
high
Token limit including reasoning
8,192 tokens
Output tokens
7,339 tokens
Cost of the attempt
$0.1101
Response time
116.8 s
API model reported in response
openai/gpt-5.4
Pinned endpoint
OpenAI | openai/gpt-5.4-20260305
Temperature
Provider default
Test protocol
community-visual-tests-v1
Technical checks
Passed, not a quality rating

Visually reviewed. This individual test does not establish overall model quality.

Earlier attempts (1)

  • Sep 7, 2026API request failedReasoning setting: high

DeepSeek-V4-Pro

The response reached the token limit. No complete recording is available.

Oct 5, 2026 · 68 s · $0.02

Not yet visually reviewed. A successful recording does not confirm correct physics or full compliance with the prompt.

Test details
Run date
Oct 5, 2026
API provider
openrouter
Requested API model
deepseek/deepseek-v4-pro-0813
Reasoning setting
high
Token limit including reasoning
8,192 tokens
Output tokens
8,192 tokens
Cost of the attempt
$0.0163
Response time
67.6 s
API model reported in response
deepseek/deepseek-v4-pro-0813
Pinned endpoint
DeepSeek | deepseek/deepseek-v4-pro-20260813
Temperature
Provider default
Test protocol
community-visual-tests-v1
Technical checks
Failed

Earlier attempts (3)

  • Oct 2, 2026API request failedReasoning setting: high
  • Oct 1, 2026API request failedReasoning setting: high
  • Sep 7, 2026API request failedReasoning setting: high
SVG short test

SVG short test

One SVG task with the same fixed settings for every model, without hidden thinking.

Prompt

Return only one standalone SVG of a pelican riding a bicycle. Use viewBox="0 0 800 600", simple shapes, two clearly visible wheels and a recognizable pelican with a long beak. At most 30 SVG elements and 1800 characters. No Markdown, explanations, comments, scripts, animation, CSS or external resources.

GPT-5.4

Unavailable in this round

DeepSeek-V4-Pro

DeepSeek-V4-Pro: SVG short test

Oct 14, 2026 · $0.0020

Test details
Test run
Oct 14, 2026
Provider
streamlake
API model
deepseek/deepseek-v4-pro-0813
Output
963 tokens
Reasoning
API reports 0 reasoning tokens
Cost of the attempt
$0.0020
Test round
43b8c5c46830

GPT-5.4 and DeepSeek-V4-Pro in the overall index

Every model with a place in the overall index, both models of this matchup highlighted. You can add or hide other models.

Overall index (Gradually Meta-Score v6)

20 of 95 models

Claude Fable 5.2max130.9
Gemini 4 Carbonhigh127.0
Claude Opus 5.5max125.7
Claude Fable 5.1max124.1
Claude Sonnet 5.5max121.9
Gemini 4 Argonhigh121.2
GPT-6 Astramax119.6
Muse Wonder Fullmax118.4
GPT-6.1 Solmax117.5
Claude Opus 5max117.3
Muse Wondermax113.7
Claude Fable 5max112.8
Kimi K3.1 Promax112.6
Muse Ember 1.0max110.5
GPT-5.6 Solmax109.3
GPT-6 Solmax108.4
Gemini 3.7 Flashhigh107.7
DeepSeek V4.1 Flash 1017max107.1
DeepSeek-V4-Promax87.1
GPT-5.4xhigh86.4

Popularity compared

How often the models are searched for, used and mentioned, on a scale from 0 to 100.

GPT-5.4 has no popularity score yet.

Over time

Weekly values from October 18, 2026 to November 16, 2026

GPT-5.4DeepSeek-V4-Pro

All data side by side

The better value is bold. For the overall index only when the gap is clear.

MetricGPT-5.4DeepSeek-V4-Pro
Intelligence
Overall indexpoints, 100 = reference group average, higher is better86.487.1
RankRank 50 of 95Rank 48 of 95
Price per 1M tokens
Inputwhat you send$2.50above 272,000 tokens: $5$0.66
Outputwhat the model writes$15above 272,000 tokens: $22.50$1.98
Cost per task (own tests)average of 1 original-protocol task both models passed (SVG short test not included)$0.23$0.021
Speed
Tokens per second6442
Popularity
Popularitysearch, usage and mentions, 0 to 100n/a75Rank 26 of 508
Technical
Context windowhow much text the model reads at once1.05 M tokens≈ 1,580 A4 pages1 M tokens≈ 1,500 A4 pages
Knowledge cutoffAug 31, 2025n/a
ReleasedMar 5, 2026Apr 24, 2026
AvailabilityActiveActive
Open weightsnoyes
  • DeepSeek-V4-Pro: At peak times (Mon, Tue, Wed, Thu, Fri, 01:00-04:00 UTC; Mon, Tue, Wed, Thu, Fri, 06:00-10:00 UTC) the price is $1.32 input and $3.96 output per 1M tokens. The table shows the off-peak price.

Prices without caching or batch discounts · Page count as a rule of thumb from Artificial Analysis

Is there a better choice?

Successor of GPT-5.4GPT-5.5

Overall index 101.4, rank 27$5 input and $30 output per 1M tokens

DeepSeek-V4-Pro vs. GPT-5.5
Cheaper than DeepSeek-V4-ProMuse Ember 1.0

Overall index 110.5, rank 14$0.10 input and $0.50 output per 1M tokens

View profile
Best model in the overall indexClaude Fable 5.2

Overall index 130.9, rank 1$8 input and $40 output per 1M tokens

Shared benchmarks

Single results from the same benchmark version, task and metric. A value is bold only with the same test setup and a clear gap.

A: GPT-5.4B: DeepSeek-V4-Pro

Code MigrationOverall · higher is betterTest setup not documented as identicalGPT-5.4: 35.0%DeepSeek-V4-Pro: 26.2%Vals AIAs of 10/29/2026
CorpFin v2Overall · higher is betterTest setup not documented as identicalGPT-5.4: 65.3%DeepSeek-V4-Pro: 61.4%Vals AIAs of 08/12/2026
GPQA DiamondOverall · higher is betterTest setup not documented as identicalGPT-5.4: 91.7%DeepSeek-V4-Pro: 89.4%Vals AIAs of 09/01/2026
LegalBenchOverall · higher is betterTest setup not documented as identicalGPT-5.4: 86.0%DeepSeek-V4-Pro: 80.3%Vals AIAs of 10/13/2026
LiveCodeBenchOverall · higher is betterTest setup not documented as identicalGPT-5.4: 84.1%DeepSeek-V4-Pro: 87.5%Vals AIAs of 09/01/2026
LMArena Code Arena WebDevOverall · higher is betterGPT-5.4: 1,400DeepSeek-V4-Pro: 1,449LMArenaAs of 11/15/2026
LMArena Text, Style ControlOverall · higher is betterGPT-5.4: 1,475DeepSeek-V4-Pro: 1,455LMArenaAs of 11/11/2026
MedCodeOverall · higher is betterTest setup not documented as identicalGPT-5.4: 41.3%DeepSeek-V4-Pro: 40.5%Vals AIAs of 10/29/2026
MedScribeOverall · higher is betterTest setup not documented as identicalGPT-5.4: 77.5%DeepSeek-V4-Pro: 75.1%Vals AIAs of 10/29/2026
MMLU ProOverall · higher is betterTest setup not documented as identicalGPT-5.4: 87.5%DeepSeek-V4-Pro: 87.2%Vals AIAs of 09/01/2026
Show 54 more benchmarks
ProgramBenchOverall · higher is betterTest setup not documented as identicalGPT-5.4: 0%DeepSeek-V4-Pro: 0%Vals AIAs of 11/05/2026
SkillsBenchOverall · higher is betterTest setup not documented as identicalGPT-5.4: 51.7%DeepSeek-V4-Pro: 51.3%Vals AIAs of 10/29/2026
SWE-bench VerifiedOverall · higher is betterTest setup not documented as identicalGPT-5.4: 78.2%DeepSeek-V4-Pro: 77.4%Vals AIAs of 09/01/2026
TaxEval v2Overall · higher is betterTest setup not documented as identicalGPT-5.4: 74.0%DeepSeek-V4-Pro: 72.1%Vals AIAs of 09/01/2026
Vibe Code Bench v1.1Overall · higher is betterTest setup not documented as identicalGPT-5.4: 67.4%DeepSeek-V4-Pro: 49.9%Vals AIAs of 11/05/2026
Code MigrationCLI · higher is betterTest setup not documented as identicalGPT-5.4: 23.8%DeepSeek-V4-Pro: 15.5%Vals AIAs of 10/29/2026
CorpFin v2Exact Pages · higher is betterTest setup not documented as identicalGPT-5.4: 64.1%DeepSeek-V4-Pro: 59.2%Vals AIAs of 08/12/2026
GPQA DiamondFew-Shot CoT · higher is betterTest setup not documented as identicalGPT-5.4: 91.4%DeepSeek-V4-Pro: 90.4%Vals AIAs of 09/01/2026
LegalBenchConclusion Tasks · higher is betterTest setup not documented as identicalGPT-5.4: 88.9%DeepSeek-V4-Pro: 89.1%Vals AIAs of 10/13/2026
LiveCodeBenchEasy · higher is betterTest setup not documented as identicalGPT-5.4: 99.1%DeepSeek-V4-Pro: 98.8%Vals AIAs of 09/01/2026
LMArena Code Arena WebDevHTML development · higher is betterGPT-5.4: 1,423DeepSeek-V4-Pro: 1,434LMArenaAs of 11/15/2026
LMArena Text, Style ControlBusiness, management and finance · higher is betterGPT-5.4: 1,482DeepSeek-V4-Pro: 1,448LMArenaAs of 11/11/2026
MMLU ProBiology · higher is betterTest setup not documented as identicalGPT-5.4: 92.9%DeepSeek-V4-Pro: 92.9%Vals AIAs of 09/01/2026
ProgramBenchAlmost Resolved · higher is betterTest setup not documented as identicalGPT-5.4: 7%DeepSeek-V4-Pro: 0%Vals AIAs of 11/05/2026
SkillsBenchNo Skills · higher is betterTest setup not documented as identicalGPT-5.4: 48.9%DeepSeek-V4-Pro: 27.2%Vals AIAs of 10/29/2026
SWE-bench Verified<15 min fix · higher is betterTest setup not documented as identicalGPT-5.4: 88.1%DeepSeek-V4-Pro: 87.6%Vals AIAs of 09/01/2026
TaxEval v2Correctness · higher is betterTest setup not documented as identicalGPT-5.4: 64.9%DeepSeek-V4-Pro: 60.6%Vals AIAs of 09/01/2026
Code MigrationCOBOL · higher is betterTest setup not documented as identicalGPT-5.4: 68.6%DeepSeek-V4-Pro: 58.4%Vals AIAs of 10/29/2026
CorpFin v2Max Fitting Context · higher is betterTest setup not documented as identicalGPT-5.4: 64.9%DeepSeek-V4-Pro: 63.1%Vals AIAs of 08/12/2026
GPQA DiamondZero-Shot CoT · higher is betterTest setup not documented as identicalGPT-5.4: 91.9%DeepSeek-V4-Pro: 88.4%Vals AIAs of 09/01/2026
LegalBenchInterpretation Tasks · higher is betterTest setup not documented as identicalGPT-5.4: 83.9%DeepSeek-V4-Pro: 75.2%Vals AIAs of 10/13/2026
LiveCodeBenchHard · higher is betterTest setup not documented as identicalGPT-5.4: 67.7%DeepSeek-V4-Pro: 72.6%Vals AIAs of 09/01/2026
LMArena Code Arena WebDevReact development · higher is betterGPT-5.4: 1,388DeepSeek-V4-Pro: 1,441LMArenaAs of 11/15/2026
LMArena Text, Style ControlChinese · higher is betterGPT-5.4: 1,505DeepSeek-V4-Pro: 1,500LMArenaAs of 11/11/2026
MMLU ProBusiness · higher is betterTest setup not documented as identicalGPT-5.4: 91.8%DeepSeek-V4-Pro: 91.9%Vals AIAs of 09/01/2026
ProgramBenchFully Resolved · higher is betterTest setup not documented as identicalGPT-5.4: 0%DeepSeek-V4-Pro: 0%Vals AIAs of 11/05/2026
SkillsBenchWith Skills · higher is betterTest setup not documented as identicalGPT-5.4: 51.7%DeepSeek-V4-Pro: 51.3%Vals AIAs of 10/29/2026
SWE-bench Verified>4 hours · higher is betterTest setup not documented as identicalGPT-5.4: 0%DeepSeek-V4-Pro: 0%Vals AIAs of 09/01/2026
TaxEval v2Stepwise Reasoning · higher is betterTest setup not documented as identicalGPT-5.4: 83.0%DeepSeek-V4-Pro: 83.6%Vals AIAs of 09/01/2026
Code MigrationCode Quality · higher is betterTest setup not documented as identicalGPT-5.4: 3.632 / 5DeepSeek-V4-Pro: 3.401 / 5Vals AIAs of 10/29/2026
CorpFin v2Shared Max Context · higher is betterTest setup not documented as identicalGPT-5.4: 66.8%DeepSeek-V4-Pro: 61.9%Vals AIAs of 08/12/2026
LegalBenchIssue Tasks · higher is betterTest setup not documented as identicalGPT-5.4: 90.5%DeepSeek-V4-Pro: 84.6%Vals AIAs of 10/13/2026
LiveCodeBenchMedium · higher is betterTest setup not documented as identicalGPT-5.4: 85.6%DeepSeek-V4-Pro: 91.1%Vals AIAs of 09/01/2026
LMArena Code Arena WebDevWeb development · higher is betterGPT-5.4: 1,400DeepSeek-V4-Pro: 1,449LMArenaAs of 11/15/2026
LMArena Text, Style ControlCoding · higher is betterGPT-5.4: 1,521DeepSeek-V4-Pro: 1,488LMArenaAs of 11/11/2026
MMLU ProChemistry · higher is betterTest setup not documented as identicalGPT-5.4: 91.1%DeepSeek-V4-Pro: 92.5%Vals AIAs of 09/01/2026
ProgramBenchRaw Pass Rate · higher is betterTest setup not documented as identicalGPT-5.4: 68.6%DeepSeek-V4-Pro: 47.8%Vals AIAs of 11/05/2026
SWE-bench Verified1-4 hours · higher is betterTest setup not documented as identicalGPT-5.4: 50.0%DeepSeek-V4-Pro: 45.2%Vals AIAs of 09/01/2026
LegalBenchRhetoric Tasks · higher is betterTest setup not documented as identicalGPT-5.4: 82.8%DeepSeek-V4-Pro: 75.3%Vals AIAs of 10/13/2026
LMArena Text, Style ControlCreative writing · higher is betterGPT-5.4: 1,440DeepSeek-V4-Pro: 1,440LMArenaAs of 11/11/2026
MMLU ProComputer Science · higher is betterTest setup not documented as identicalGPT-5.4: 89.8%DeepSeek-V4-Pro: 89.0%Vals AIAs of 09/01/2026
SWE-bench Verified15 min - 1 hour · higher is betterTest setup not documented as identicalGPT-5.4: 76.2%DeepSeek-V4-Pro: 75.9%Vals AIAs of 09/01/2026
LegalBenchRule Tasks · higher is betterTest setup not documented as identicalGPT-5.4: 84.0%DeepSeek-V4-Pro: 77.4%Vals AIAs of 10/13/2026
LMArena Text, Style ControlEnglish · higher is betterGPT-5.4: 1,476DeepSeek-V4-Pro: 1,467LMArenaAs of 11/11/2026
MMLU ProEconomics · higher is betterTest setup not documented as identicalGPT-5.4: 89.7%DeepSeek-V4-Pro: 88.9%Vals AIAs of 09/01/2026
LMArena Text, Style ControlEntertainment, sports and media · higher is betterGPT-5.4: 1,441DeepSeek-V4-Pro: 1,432LMArenaAs of 11/11/2026
MMLU ProEngineering · higher is betterTest setup not documented as identicalGPT-5.4: 85.2%DeepSeek-V4-Pro: 86.7%Vals AIAs of 09/01/2026
LMArena Text, Style ControlExcluding ties · higher is betterGPT-5.4: 1,484DeepSeek-V4-Pro: 1,457LMArenaAs of 11/11/2026
MMLU ProHealth · higher is betterTest setup not documented as identicalGPT-5.4: 82.4%DeepSeek-V4-Pro: 82.4%Vals AIAs of 09/01/2026
LMArena Text, Style ControlExpert prompts · higher is betterGPT-5.4: 1,514DeepSeek-V4-Pro: 1,475LMArenaAs of 11/11/2026
MMLU ProHistory · higher is betterTest setup not documented as identicalGPT-5.4: 79.3%DeepSeek-V4-Pro: 77.7%Vals AIAs of 09/01/2026
LMArena Text, Style ControlFrench prompts · higher is betterGPT-5.4: 1,501DeepSeek-V4-Pro: 1,468LMArenaAs of 11/11/2026
MMLU ProLaw · higher is betterTest setup not documented as identicalGPT-5.4: 75.5%DeepSeek-V4-Pro: 74.0%Vals AIAs of 09/01/2026
LMArena Text, Style ControlGerman prompts · higher is betterGPT-5.4: 1,476DeepSeek-V4-Pro: 1,460LMArenaAs of 11/11/2026

More comparisons

Compare GPT-5.4 and DeepSeek-V4-Pro with the models people compare them with most often.

Compare another matchup

The most popular comparisons

  1. 1Claude Opus 5.5 vs. DeepSeek-V4-Pro
  2. 2DeepSeek-V4-Pro vs. DeepSeek-V4.1-Flash
  3. 3GPT-6 Luna vs. DeepSeek-V4-Pro
  4. 4Claude Sonnet 5.5 vs. DeepSeek-V4-Pro
  5. 5Gemini 3.8 Flash vs. DeepSeek-V4-Pro
  6. 6GPT-6 Luna vs. GPT-5.4
  7. 7Claude Opus 5 vs. DeepSeek-V4-Pro
  8. 8DeepSeek-V4-Pro vs. Qwen 3.8 27B
  9. 9Grok 4.7 vs. DeepSeek-V4-Pro
Show all 42 comparisons
  1. 10Claude Haiku 5.5 vs. DeepSeek-V4-Pro
  2. 11DeepSeek-V4-Pro vs. DeepSeek V4.1 Flash 1017
  3. 12DeepSeek-V4-Pro vs. MiMo-V2.5-Pro
  4. 13DeepSeek-V4-Pro vs. Kimi K3
  5. 14GPT-5.6 Sol vs. DeepSeek-V4-Pro
  6. 15GPT-5.4 vs. GLM-5.3-Flash
  7. 16DeepSeek-V4-Pro vs. GLM-5.3
  8. 17DeepSeek-V4-Pro vs. Qwen 3.8 Max 0902
  9. 18DeepSeek-V4-Pro vs. MiMo-V2.5
  10. 19GPT-6 Sol vs. GPT-5.4
  11. 20DeepSeek-V4-Pro vs. GLM-5.3-Flash
  12. 21DeepSeek-V4-Pro vs. Mistral Large 4
  13. 22GPT-5.6 Luna vs. DeepSeek-V4-Pro
  14. 23DeepSeek-V4-Pro vs. Kimi K3.1 Pro
  15. 24DeepSeek-V4-Pro vs. DeepSeek-V4-Flash
  16. 25DeepSeek-V4-Pro vs. GLM-5.2
  17. 26Claude Sonnet 5 vs. DeepSeek-V4-Pro
  18. 27GPT-6 Sol vs. DeepSeek-V4-Pro
  19. 28GPT-5.6 Luna vs. GPT-5.4
  20. 29GPT-5.4 vs. GLM-5.3
  21. 30Claude Sonnet 5.5 vs. GPT-5.4
  22. 31GPT-6 Astra vs. GPT-5.4
  23. 32DeepSeek-V4-Pro vs. Mistral Medium 3.5
  24. 33Claude Opus 5.5 vs. GPT-5.4
  25. 34GPT-5.6 Terra vs. GPT-5.4
  26. 35GPT-5.6 Sol vs. GPT-5.4
  27. 36Claude Opus 4.5 vs. DeepSeek-V4-Pro
  28. 37Claude Fable 5 vs. GPT-5.4
  29. 38GPT-6.1 Sol vs. GPT-5.4
  30. 39Gemini 4 Argon vs. DeepSeek-V4-Pro
  31. 40GPT-6.1 Terra vs. GPT-5.4
  32. 41GPT-6.1 Terra vs. DeepSeek-V4-Pro
  33. 42Gemini 4 Carbon vs. DeepSeek-V4-Pro