Skip to main content

Google DeepMindLLM matchup

Gemini 4 Neonvs.Gemini 4 Argon

Is the higher price worth it?

Gemini 4 Neon and Gemini 4 Argon perform about equally well, but Gemini 4 Neon costs 1.5 times as much.

level
IntelligenceOverall index, 100 points = average
127.1

Gemini 4 Neon

Rank 3

121.5

Gemini 4 Argon

Rank 8

SpeedTokens per second
n/a

Gemini 4 Neon

36

Gemini 4 Argon

Gemini 4 Argon cheaper until Nov 30
Price$ per 1M tokens
$6

Gemini 4 Neon

$4

Gemini 4 Argon

Choose Gemini 4 Neon for

AgentsFinanceGeneralLegal (not certain)

No clear advantage for Gemini 4 Argon.

Where is the difference?

Strengths at a glance

Gemini 4 NeonGemini 4 Argon

The median of all ranked models is below 105 in every area, so it sits in the centre of the net.

115125135105CodinglevelReasoninglevelAgentsGemini 4 NeonGeneralGemini 4 NeonFinanceGemini 4 NeonLegalslightlyGemini 4 Neon
Codinglevel
Gemini 4 Neon126.2Rank 5
Gemini 4 Argon123.6Rank 8
Median of ranked models84.3

95 % range: Gemini 4 Neon 120.1 to 132.2, Gemini 4 Argon 115.9 to 131.2.

AreaGemini 4 NeonGemini 4 Argon

The same values and verdicts as the bars below. In the close-up the net starts at 105 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, Multimodal, Health.

Gemini 4 Neon is ahead in 3 of 9 areas, Gemini 4 Argon in none.

Gemini 4 Neon ahead: 3Gemini 4 Neon slightly ahead: 1level: 2too little data: 3

Areas in the overall index
AgentsGemini 4 Neon +9122.6 to 113.9
GeneralGemini 4 Neon +5125.1 to 120.3
Codinglevel126.2 to 123.6
Reasoninglevel121.3 to 119.5
Knowledgetoo little data135.6 to 126.5
Mathematicsonly Gemini 4 Argon has a score
Specialist fields
FinanceGemini 4 Neon +5127.7 to 122.5
Legalleaning Gemini 4 Neonnot certain · 2 and 4 tests
Healthonly Gemini 4 Argon 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.

Show 3 more areas that do not count toward the overall index
Cybersecurityonly Gemini 4 Argon has a score
Productivityonly Gemini 4 Argon has a score
Educationonly Gemini 4 Argon 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.

Gemini 4 Neon vs. Gemini 4 Argon at the same effort

Both models measured at the same reasoning efforts. This shows whether a lead comes from the model or only from more compute.

highGemini 4 Neon ahead
8.9 points gap across 9 shared test series
Overall index (xhigh vs. high)Gemini 4 Neon slightly ahead
Gemini 4 Neon 127.1 vs. Gemini 4 Argon 121.5

The gap compares only the Artificial Analysis test series in which both models are measured at that effort. Tied below 3 points, ahead only beyond two standard errors.

Which model for which task?

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

Writing and debugging codelevelCoding 126.2 to 123.6
Maths and data analysislevelMathematics without a score for Gemini 4 Neon, Reasoning 121.3 to 119.5
Facts and researchopenKnowledge 135.6 to 126.5 (too little data)
Agents and workflowsGemini 4 NeonAgents 122.6 to 113.9
Security analysisopenCybersecurity without a score for Gemini 4 Neon
Many requests on a small budgetGemini 4 Argon$6 to $4 per 1M tokens; from December 1 $6 to $8
Finance, legal and medical textsGemini 4 NeonFinance 127.7 to 122.5, Legal 126.6 to 120.2, Health without a score for Gemini 4 Neon

Gemini 4 Neon vs. Gemini 4 Argon in our own test

There is no shared test round for this selection. Results from different rounds are not mixed.

Gemini 4 Neon and Gemini 4 Argon 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 99 models

Claude Fable 5.2max130.3
Gemini 4 Carbonhigh127.8
Gemini 4 Neonxhigh127.1
GPT-6.2 Astramax126.6
Claude Opus 5.5max125.0
Claude Fable 5.1max124.1
Claude Sonnet 5.5max121.9
Gemini 4 Argonhigh121.5
GPT-6 Astramax119.6
GPT-6.2 Solmax119.2
Muse Wonder Fullmax117.9
GPT-6.1 Solmax117.3
Claude Opus 5max117.1
Muse Wondermax113.5
Claude Fable 5max112.8
Kimi K3.1 Promax112.4
Muse Ember 1.0max111.1
GPT-5.6 Solmax109.5
GPT-6 Solmax108.3
Gemini 3.7 Flashhigh107.8

All data side by side

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

MetricGemini 4 NeonGemini 4 Argon
Intelligence
Overall indexpoints, 100 = reference group average, higher is better127.1121.5
RankRank 3 of 99Rank 8 of 99
Price per 1M tokens
Inputwhat you send$3$2
Outputwhat the model writes$15$10
Speed
Tokens per secondn/a36
Technical
Context windowsource-reported context limit1.05 M tokens≈ 1,570 A4 pages1.05 M tokens≈ 1,570 A4 pages
Knowledge cutoffMarch 2026n/a
ReleasedNov 18, 2026Oct 13, 2026
AvailabilityActiveActive
Open weightsnono
  • Gemini 4 Neon, Billing: The output price includes reasoning tokens. Cache hits are billed through implicit caching. Source
  • Gemini 4 Neon, Batch, Flex, and Priority: Batch and Flex cost half the Standard rate. Priority costs 1.8 times the Standard rate. These multipliers apply to input, output, and cache hits. Source
  • Gemini 4 Argon, Standard pricing through November 30, 2026: Per 1 million tokens: $2.00 input, $10.00 output including thinking, and $0.10 cached input. Source
  • Gemini 4 Argon, Standard pricing from December 1, 2026: Per 1 million tokens: $4.00 input, $20.00 output including thinking, and $0.20 cached input. Source
  • Gemini 4 Argon, Caching: Implicit caching only; explicit caching is not supported. Source

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

Is there a better choice?

Successor of Gemini 4 ArgonGemini 4 Carbon

Overall index 127.8, rank 2$2 input and $10 output per 1M tokens

Gemini 4 Neon vs. Gemini 4 Carbon
As cheap as Gemini 4 ArgonClaude Sonnet 5.5

Overall index 121.9, rank 7$2 input and $10 output per 1M tokens

View profile
Best model in the overall indexClaude Fable 5.2

Overall index 130.3, rank 1$8 input and $40 output per 1M tokens

Gemini 4 Neon vs. Claude Fable 5.2

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: Gemini 4 NeonB: Gemini 4 Argon

AA-BriefcaseOverall · higher is betterGemini 4 Neon: 1,632.0 eloGemini 4 Argon: 1,485.1 eloArtificial AnalysisAs of 11/20/2026
AA-OmniscienceOverall · higher is betterGemini 4 Neon: 53.8 pointsGemini 4 Argon: 46.1 pointsArtificial AnalysisAs of 11/20/2026
AA-Omniscience AccuracyOverall · higher is betterGemini 4 Neon: 59.4%Gemini 4 Argon: 48.3%Artificial AnalysisAs of 11/20/2026
AA-Omniscience Hallucination RateOverall · lower is betterGemini 4 Neon: 13.9%Gemini 4 Argon: 4.3%Artificial AnalysisAs of 11/20/2026
AutomationBench-AAOverall · higher is betterGemini 4 Neon: 79.2%Gemini 4 Argon: 77.5%Artificial AnalysisAs of 11/20/2026
CritPt v2 (Hard Subset)Overall · higher is betterGemini 4 Neon: 59.0%Gemini 4 Argon: 52.5%Artificial AnalysisAs of 11/20/2026
FrontierCodeOverall · higher is betterGemini 4 Neon: 43.3%Gemini 4 Argon: 25.7%Artificial AnalysisAs of 11/20/2026
GDP.pdfOverall · higher is betterGemini 4 Neon: 33.4%Gemini 4 Argon: 21.8%Artificial AnalysisAs of 11/20/2026
HLE-DiamondOverall · higher is betterGemini 4 Neon: 68.4%Gemini 4 Argon: 56.7%Artificial AnalysisAs of 11/20/2026
Terminal-BenchOverall · higher is betterGemini 4 Neon: 61.6%Gemini 4 Argon: 57.1%Artificial AnalysisAs of 11/20/2026
Show 1 more benchmarks
Terminal-Bench-ScienceOverall · higher is betterGemini 4 Neon: 65.7%Gemini 4 Argon: 52.9%Artificial AnalysisAs of 11/20/2026

More comparisons

Compare Gemini 4 Neon and Gemini 4 Argon with the models people compare them with most often.

Compare another matchup

The most popular comparisons

  1. 1Claude Fable 5.2 vs. Gemini 4 Neon
  2. 2GPT-6.1 Terra vs. Gemini 4 Neon
  3. 3Claude Opus 5.5 vs. Gemini 4 Argon
  4. 4Claude Fable 5.2 vs. Gemini 4 Argon
  5. 5GPT-6 Astra vs. Gemini 4 Argon
  6. 6GPT-5.6 Sol vs. Gemini 4 Argon
  7. 7Claude Sonnet 4.5 vs. Gemini 4 Argon
  8. 8GPT-6.1 Terra vs. Gemini 4 Argon
  9. 9Gemini 4 Argon vs. DeepSeek V4.1 Flash 1017
Show all 45 comparisons
  1. 10GPT-6 Luna vs. Gemini 4 Argon
  2. 11Claude Sonnet 5 vs. Gemini 4 Argon
  3. 12Claude Opus 4.6 vs. Gemini 4 Argon
  4. 13Gemini 4 Argon vs. DeepSeek-V4-Flash
  5. 14Gemini 4 Argon vs. Kimi K3.1 Pro
  6. 15Gemini 4 Argon vs. Qwen 3.8 27B
  7. 16Claude Sonnet 5.5 vs. Gemini 4 Argon
  8. 17Gemini 4 Argon vs. Gemini 3.6 Flash
  9. 18Gemini 4 Argon vs. GLM-5.3
  10. 19Gemini 4 Neon vs. Gemini 4 Carbon
  11. 20Gemini 4 Argon vs. Grok 4.5
  12. 21Gemini 4 Argon vs. Kimi K3
  13. 22Gemini 4 Argon vs. DeepSeek-V4.1-Flash
  14. 23GPT-6.1 Sol vs. Gemini 4 Argon
  15. 24GPT-5.6 Luna vs. Gemini 4 Argon
  16. 25Claude Fable 5 vs. Gemini 4 Argon
  17. 26Claude Haiku 5.5 vs. Gemini 4 Argon
  18. 27Claude Opus 4.5 vs. Gemini 4 Argon
  19. 28Gemini 4 Argon vs. DeepSeek-V4-Pro
  20. 29Gemini 4 Argon vs. Gemini 3.5 Flash-Lite
  21. 30Gemini 4 Argon vs. Qwen 3.8 Max 0902
  22. 31Claude Sonnet 4.6 vs. Gemini 4 Argon
  23. 32Gemini 4 Argon vs. GLM-5.3-Flash
  24. 33GPT-5.6 Terra vs. Gemini 4 Argon
  25. 34Gemini 4 Argon vs. Gemini 3.1 Pro Preview
  26. 35Gemini 4 Argon vs. GLM-5.2
  27. 36Claude Opus 4.8 vs. Gemini 4 Argon
  28. 37Claude Haiku 4.5 vs. Gemini 4 Argon
  29. 38Gemini 4 Argon vs. Grok 4.7
  30. 39Gemini 4 Argon vs. Kimi K2.6
  31. 40Claude Opus 4.7 vs. Gemini 4 Argon
  32. 41GPT-6.2 Astra vs. Gemini 4 Neon
  33. 42GPT-6.2 Sol vs. Gemini 4 Neon
  34. 43Claude Opus 5 vs. Gemini 4 Argon
  35. 44Claude Fable 5.1 vs. Gemini 4 Argon
  36. 45Gemini 4 Argon vs. Gemini 3.8 Flash