Enter opens the highlighted result. Esc closes.

DeepSeek V4 Pro 0813 vs Gemini 4 Argon

Updated October 21, 2026. 65 benchmarks have a result for both. Coding is ranked on the Vibe Coding Index; every other board is shown as published.

Replace DeepSeek V4 Pro 0813 Replace Gemini 4 Argon
DeepSeek V4 Pro 0813DeepSeek
Coding
54.6
Overall
36.0
Output $/M
$1.98
1
Gemini 4 ArgonGoogle
Coding
80.5
Overall
52.6
Output $/M
$10.00
64
vs boards won of 65 shared

Decision reading

Pick Gemini 4 Argon for coding: it scores 80.5 on the Vibe Coding Index against 54.6 for DeepSeek V4 Pro 0813.

Pick DeepSeek V4 Pro 0813 when output tokens cost 5.1x less, or when the benchmark that matters is Long context reasoning (AA-LCR), where it leads.

Model ADeepSeek V4 Pro 0813DeepSeek54.6/1001 independent benchmark$0.10 per solved taskModel BGemini 4 ArgonGoogle80.5/1002 independent benchmarksNo cost per solved task
Shared results
65
DeepSeek V4 Pro 0813 only
13
Gemini 4 Argon only
27
Like-for-like categories
7 of 9

Shared results can support a head-to-head reading. Results only one model has describe coverage, not superiority.

Which one for your work

Each card is decided by one number both models carry. Where only one has it, the card says so and makes no call.

At a glance

Coding index
DeepSeek V4 Pro 0813 54.6 from 1 benchmark, Gemini 4 Argon 80.5 from 2 benchmarks.
Widest category
Math, 26.4 points apart on average over 6 shared benchmarks.
Widest single gap
FrontierMath, tier 4: DeepSeek V4 Pro 0813 26.8% against Gemini 4 Argon 78.0%, 51.2 points apart on a 0 to 100 scale.
Output price
DeepSeek V4 Pro 0813 $1.98 against Gemini 4 Argon $10.00 per million output tokens, 5.1x apart.
Context window
Both take 1.05M tokens.

Benchmark by benchmark

First the score: boards each model leads, per category, where both have a result. Then every board, a category to a fold; bars are each result on a 0 to 100 scale, so compare the two in a row, not one row with another.

Boards won, where both have a result
CategoryDeepSeek V4 Pro 0813BarsGemini 4 ArgonTies
Coding016
Intelligence02
Agentic work08
Reasoning09
Math06
Knowledge07
General116
All shared boards164
CodingLike-for-likeFour of these boards feed the Vibe Coding Index016
Coding benchmarks for DeepSeek V4 Pro 0813 and Gemini 4 Argon
BenchmarkDeepSeek V4 Pro 0813Gemini 4 ArgonLeader
LiveBench codingNot measured89.7%Only Gemini 4 Argon measured
LMArena WebDev15821678Gemini 4 Argon
AA Coding Index68.8Not measuredOnly DeepSeek V4 Pro 0813 measured
LiveCodeBench (Vals AI)87.5%Not measuredOnly DeepSeek V4 Pro 0813 measured
SWE-bench Verified (Vals AI)96.4%Not measuredOnly DeepSeek V4 Pro 0813 measured
Terminal-Bench 4 (Vals AI)14.1%57.6%Gemini 4 Argon
Vibe Code Bench (Vals AI)82.3%91.9%Gemini 4 Argon
Code migration (Vals AI)41.5%68.2%Gemini 4 Argon
ProgramBench (Vals AI)0.0%2.5%Gemini 4 Argon
IOI (Vals AI)51.6%100.0%Gemini 4 Argon
Terminal-Bench 2.1 (Vals AI)54.7%57.7%Gemini 4 Argon
SWE-bench Multimodal (Vals AI)Not measured56.0%Only Gemini 4 Argon measured
Vibe Code Bench 1-100 (Vals AI)17.5%21.2%Gemini 4 Argon
SkillsBench (Vals AI)53.8%Not measuredOnly DeepSeek V4 Pro 0813 measured
CyberBench (Vals AI)72.9%77.9%Gemini 4 Argon
SciCode51.0%61.8%Gemini 4 Argon
FrontierCode28.5%47.5%Gemini 4 Argon
FrontierSWENot measured55.0%Only Gemini 4 Argon measured
WeirdML66.2%Not measuredOnly DeepSeek V4 Pro 0813 measured
ALE-Bench1403.22100.1Gemini 4 Argon
LMArena Text: coding14691546Gemini 4 Argon
LMArena Text: software and IT14621556Gemini 4 Argon
LMArena WebDev: React15881692Gemini 4 Argon
LMArena WebDev: HTML15661643Gemini 4 Argon
Neither model has a result on the other 14 boards here
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index02
Intelligence benchmarks for DeepSeek V4 Pro 0813 and Gemini 4 Argon
BenchmarkDeepSeek V4 Pro 0813Gemini 4 ArgonLeader
AA Intelligence Index36.052.6Gemini 4 Argon
Epoch Capabilities Index155.6166.4Gemini 4 Argon
Agentic workLike-for-likePublic boards, shown as published, kept out of the index08
Agentic work benchmarks for DeepSeek V4 Pro 0813 and Gemini 4 Argon
BenchmarkDeepSeek V4 Pro 0813Gemini 4 ArgonLeader
AA Agentic Index41.3Not measuredOnly DeepSeek V4 Pro 0813 measured
Design Arena: spreadsheetsNot measured1151Only Gemini 4 Argon measured
LiveBench researchNot measured83.1%Only Gemini 4 Argon measured
LiveBench browserNot measured92.0%Only Gemini 4 Argon measured
LiveBench long agenticNot measured69.9%Only Gemini 4 Argon measured
SREBench (Vals AI)1.9%44.3%Gemini 4 Argon
Finance Agent (Vals AI)50.4%65.4%Gemini 4 Argon
Tax Agent Bench (Vals AI)26.8%44.6%Gemini 4 Argon
Legal Research Bench (Vals AI)40.9%54.8%Gemini 4 Argon
Harvey's Legal Agent Benchmark (Vals AI)10.8%27.1%Gemini 4 Argon
Excel Modeling Benchmark (Vals AI)52.8%75.2%Gemini 4 Argon
BioMysteryBench (Vals AI)Not measured76.3%Only Gemini 4 Argon measured
Terminal-Bench-Science (Vals AI)4.3%44.3%Gemini 4 Argon
Vals Science IndexNot measured55.4%Only Gemini 4 Argon measured
Time Horizon Index (Vals AI)Not measured52.5%Only Gemini 4 Argon measured
CUA-bench (Vals AI)Not measured4.8%Only Gemini 4 Argon measured
Robo-bench (Vals AI)Not measured0.8%Only Gemini 4 Argon measured
APEX-Agents47.3%82.4%Gemini 4 Argon
Vending-Bench 2Not measured$13,718Only Gemini 4 Argon measured
Neither model has a result on the other 20 boards here
ReasoningLike-for-likePublic boards, shown as published, kept out of the index09
Reasoning benchmarks for DeepSeek V4 Pro 0813 and Gemini 4 Argon
BenchmarkDeepSeek V4 Pro 0813Gemini 4 ArgonLeader
GPQA Diamond92.4%Not measuredOnly DeepSeek V4 Pro 0813 measured
LiveBench reasoningNot measured95.1%Only Gemini 4 Argon measured
MysteryMechanism (Vals AI)Not measured45.5%Only Gemini 4 Argon measured
GPQA Diamond (Artificial Analysis run)92.8%Not measuredOnly DeepSeek V4 Pro 0813 measured
Humanity's Last Exam (Artificial Analysis run)41.0%57.1%Gemini 4 Argon
GPQA Diamond (Epoch AI run)91.7%96.4%Gemini 4 Argon
ARC-AGI90.5%98.5%Gemini 4 Argon
ARC-AGI-261.3%91.3%Gemini 4 Argon
Chess puzzles46.0%59.0%Gemini 4 Argon
Mystery game puzzles43.0%64.0%Gemini 4 Argon
EBR-benchNot measured64.8%Only Gemini 4 Argon measured
LMArena Text: hard prompts14581546Gemini 4 Argon
LMArena Text: expert14591550Gemini 4 Argon
LMArena Text: hard prompts in English14631548Gemini 4 Argon
Neither model has a result on the other 7 boards here
MathLike-for-likePublic boards, shown as published, kept out of the index06
Math benchmarks for DeepSeek V4 Pro 0813 and Gemini 4 Argon
BenchmarkDeepSeek V4 Pro 0813Gemini 4 ArgonLeader
OTIS Mock AIME98.6%100.0%Gemini 4 Argon
FrontierMath, tiers 1 to 364.6%86.0%Gemini 4 Argon
FrontierMath, tier 426.8%78.0%Gemini 4 Argon
ProofBench50.0%99.0%Gemini 4 Argon
LMArena Text: math14411536Gemini 4 Argon
LMArena Text: mathematical work14431557Gemini 4 Argon
Neither model has a result on the other 7 boards here
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index07
Knowledge benchmarks for DeepSeek V4 Pro 0813 and Gemini 4 Argon
BenchmarkDeepSeek V4 Pro 0813Gemini 4 ArgonLeader
MMLU Pro87.0%Not measuredOnly DeepSeek V4 Pro 0813 measured
LegalBench (Vals AI)82.4%88.3%Gemini 4 Argon
CorpFin (Vals AI)65.4%Not measuredOnly DeepSeek V4 Pro 0813 measured
TaxEval (Vals AI)73.1%Not measuredOnly DeepSeek V4 Pro 0813 measured
MedCode (Vals AI)42.5%58.8%Gemini 4 Argon
SimpleQA Verified52.9%76.0%Gemini 4 Argon
LMArena Text: science14571548Gemini 4 Argon
LMArena Text: medicine and healthcare14461555Gemini 4 Argon
LMArena Text: legal and government14591548Gemini 4 Argon
LMArena Text: business and finance14421525Gemini 4 Argon
Neither model has a result on the other 7 boards here
Web designDirectional onlyPublic boards, shown as published, kept out of the index7 boards, none shared
Web design benchmarks for DeepSeek V4 Pro 0813 and Gemini 4 Argon
BenchmarkDeepSeek V4 Pro 0813Gemini 4 ArgonLeader
Design Arena: websitesNot measured1315Only Gemini 4 Argon measured
Design Arena: UI componentsNot measured1333Only Gemini 4 Argon measured
Design Arena: game devNot measured1377Only Gemini 4 Argon measured
Design Arena: data vizNot measured1334Only Gemini 4 Argon measured
Design Arena: 3DNot measured1389Only Gemini 4 Argon measured
Design Arena: all code categoriesNot measured1328Only Gemini 4 Argon measured
LiveBench designNot measured73.7%Only Gemini 4 Argon measured
Neither model has a result on the other 2 boards here
GeneralLike-for-likePublic boards, shown as published, kept out of the index116
General benchmarks for DeepSeek V4 Pro 0813 and Gemini 4 Argon
BenchmarkDeepSeek V4 Pro 0813Gemini 4 ArgonLeader
Vals Index53.0%69.2%Gemini 4 Argon
LiveBench data analysisNot measured85.2%Only Gemini 4 Argon measured
Public Benefits Bench (Vals AI)Not measured69.8%Only Gemini 4 Argon measured
SAGE (Vals AI)Not measured53.6%Only Gemini 4 Argon measured
MedScribe (Vals AI)80.2%87.4%Gemini 4 Argon
Long context reasoning (AA-LCR)80.3%79.7%DeepSeek V4 Pro 0813
DTBench93.9%97.6%Gemini 4 Argon
LMCA45.5%63.7%Gemini 4 Argon
Furniture assemblyNot measured72.5%Only Gemini 4 Argon measured
LMArena Text14461532Gemini 4 Argon
LMArena Text: instruction following14481534Gemini 4 Argon
LMArena Text: creative writing14391527Gemini 4 Argon
LMArena Text: English14571538Gemini 4 Argon
LMArena Text: non-English14311522Gemini 4 Argon
LMArena Text: Chinese14811611Gemini 4 Argon
LMArena Text: Korean1449Not measuredOnly DeepSeek V4 Pro 0813 measured
LMArena Text: French1446Not measuredOnly DeepSeek V4 Pro 0813 measured
LMArena Text: Spanish14351503Gemini 4 Argon
LMArena Text: Russian14481534Gemini 4 Argon
LMArena Text: multi-turn14541556Gemini 4 Argon
LMArena Text: longer queries14581547Gemini 4 Argon
LMArena Text: writing and language14431529Gemini 4 Argon
LMArena Text: entertainment and media14241527Gemini 4 Argon
Neither model has a result on the other 23 boards here
Image generationNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
Image generation benchmarks for DeepSeek V4 Pro 0813 and Gemini 4 Argon
BenchmarkDeepSeek V4 Pro 0813Gemini 4 ArgonLeader
Neither model has a result on 5 boards here

What each workload costs

Three fixed token mixes at each model's listed price, so per-token rates become a bill.

Chat turn

1K input + 500 output tokens

DeepSeek V4 Pro 0813$0.0016Fits in one request
Gemini 4 Argon$0.0070Fits in one request

DeepSeek V4 Pro 0813 costs less

Repository review

50K input + 3K output tokens

DeepSeek V4 Pro 0813$0.039Fits in one request
Gemini 4 Argon$0.130Fits in one request

DeepSeek V4 Pro 0813 costs less

Agent loop

200K input + 10K output tokens

DeepSeek V4 Pro 0813$0.152Fits in one request
Gemini 4 Argon$0.500Fits in one request

DeepSeek V4 Pro 0813 costs less

Listed OpenRouter rates, without cache or batch discounts. A workload that does not fit a model's context window would need splitting.

Specification differences

The leading value in a row is marked; a row with a missing value names no leader. Our two rows are marked in red.

Specifications of DeepSeek V4 Pro 0813 and Gemini 4 Argon
SpecificationDeepSeek V4 Pro 0813Google Gemini 4 Argon
MakerDeepSeekGoogle
WeightsOpen weightsNo public weights listed
ReleasedAugust 12, 2026October 13, 2026
Context window1.05M1.05M
Input $/Mtok$0.66$2.00
Output $/Mtok$1.98$10.00
Coding index54.680.5
Independent measurements behind it12
Cost per solved task$0.10Not computable
SourceOpenRouter listingOpenRouter listing

Questions

Is DeepSeek V4 Pro 0813 better than Gemini 4 Argon for coding?

Pick Gemini 4 Argon for coding: it scores 80.5 on the Vibe Coding Index against 54.6 for DeepSeek V4 Pro 0813. Pick DeepSeek V4 Pro 0813 when output tokens cost 5.1x less, or when the benchmark that matters is Long context reasoning (AA-LCR), where it leads.

Which is cheaper, DeepSeek V4 Pro 0813 or Gemini 4 Argon?

DeepSeek V4 Pro 0813 costs $0.66 per million input tokens and $1.98 per million output tokens; Gemini 4 Argon costs $2.00 and $10.00. Cost per solved task is known for DeepSeek V4 Pro 0813 only.

Which has the bigger context window, DeepSeek V4 Pro 0813 or Gemini 4 Argon?

Neither: both take 1.05M tokens.

How many benchmarks is the DeepSeek V4 Pro 0813 vs Gemini 4 Argon comparison based on?

65 benchmarks have a result for both models as of October 21, 2026. DeepSeek V4 Pro 0813's coding index rests on 1 independent benchmark and Gemini 4 Argon's on 2. Where only one model has a result, the page says so instead of naming a winner.

Compare next