Skip to main content

AnthropicGoogle DeepMindLLM matchup

Claude Haiku 5.5vs.Gemini 4 Argon

Which one is better?

Gemini 4 Argon performs better than Claude Haiku 5.5, but costs 20 times as much.

Gemini 4 Argon ahead
IntelligenceOverall index, 100 points = average
103.4

Claude Haiku 5.5

Rank 20

122.3

Gemini 4 Argon

Rank 5

Haiku 5.5 faster
SpeedTokens per second
236

Claude Haiku 5.5

74

Gemini 4 Argon

Haiku 5.5 cheaper
Price$ per 1M tokens
$0.20

Claude Haiku 5.5

$4

Gemini 4 Argon

Gemini 4 Argon more popular
Popularity0 to 100
77

Claude Haiku 5.5

Rank 3 of 875

92

Gemini 4 Argon

Rank 1 of 875

Above 100,000 tokens of context, Claude Haiku 5.5 costs more: $0.50 input and $2.50 output per 1M tokens.

Choose Claude Haiku 5.5 for

No clear advantage

Choose Gemini 4 Argon for

KnowledgeLegalProductivityCybersecurityFinanceGeneralCodingReasoningHealthMathematicsEducationAgents

Where is the difference?

Strengths at a glance

Haiku 5.5Gemini 4 Argon

The median of all ranked models is below 100 in every area, so it sits in the centre of the net.

110120130100CodingGemini 4 ArgonReasoningGemini 4 ArgonMathematicsGemini 4 ArgonKnowledgeGemini 4 ArgonAgentsGemini 4 ArgonGeneralGemini 4 ArgonFinanceGemini 4 ArgonLegalGemini 4 ArgonHealthGemini 4 Argon
CodingGemini 4 Argon ahead
Haiku 5.5106.2Rank 18
Gemini 4 Argon121.9Rank 6
Median of ranked models83.7

95 % range: Haiku 5.5 102.5 to 109.9, Gemini 4 Argon 114.8 to 128.9.

AreaHaiku 5.5Gemini 4 Argon

The same values and verdicts as the bars below. In the top field the net starts at 100 points, the reference group average; values below sit as a hollow point in the centre. Not in the net because a model has no own value there or the data are too thin: Multimodal.

Gemini 4 Argon is ahead in 9 of 9 areas, Haiku 5.5 in none.

Gemini 4 Argon ahead: 9

Areas in the overall index
KnowledgeGemini 4 Argon +4185.5 to 127.0
GeneralGemini 4 Argon +16106.4 to 122.2
CodingGemini 4 Argon +16106.2 to 121.9
ReasoningGemini 4 Argon +15105.2 to 119.8
MathematicsGemini 4 Argon +12107.1 to 119.6
AgentsGemini 4 Argon +9106.1 to 114.9
Specialist fields
LegalGemini 4 Argon +2694.4 to 120.9
FinanceGemini 4 Argon +16104.7 to 121.1
HealthGemini 4 Argon +14108.9 to 122.6

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
ProductivityGemini 4 Argon +19101.8 to 121.3
CybersecurityGemini 4 Argon +17108.6 to 125.8
EducationGemini 4 Argon +11109.6 to 120.2

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.

Claude Haiku 5.5 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 Argon ahead
Haiku 5.5 96.6 vs. Gemini 4 Argon 122.3 · Gap 20.1 · Test series 11
Overall index (max vs. high)Gemini 4 Argon ahead
Haiku 5.5 103.4 vs. Gemini 4 Argon 122.3

Gap and verdict compare 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. The single values rest on all test series of each model, so their difference can deviate from the gap.

Which model for which task?

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

Writing and debugging codeGemini 4 ArgonCoding 106.2 to 121.9
Maths and data analysisGemini 4 ArgonMathematics 107.1 to 119.6, Reasoning 105.2 to 119.8
Facts and researchGemini 4 ArgonKnowledge 85.5 to 127.0
Agents and workflowsGemini 4 ArgonAgents 106.1 to 114.9
Fast chat repliesHaiku 5.5236 to 74 tokens per second
Security analysisGemini 4 ArgonCybersecurity 108.6 to 125.8
Many requests on a small budgetHaiku 5.5$0.20 to $4 per 1M tokens; from December 1 $0.20 to $8
Finance, legal and medical textsGemini 4 ArgonFinance 104.7 to 121.1, Legal 94.4 to 120.9, Health 108.9 to 122.6

See for yourself: same task, one attempt

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.

Claude Haiku 5.5

Unavailable in this round

Gemini 4 Argon

Unavailable in this round

Claude Haiku 5.5 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 v4)

20 of 91 models

4 models in this view are measured at a lower reasoning effort than max in the overall index. Dashed column: lower reasoning effort than the top.

Claude Opus 5.5max126.1
Gemini 4 Carbonhigh125.7
Claude Fable 5.1max123.8
Claude Sonnet 5.5max122.8
Gemini 4 Argonhigh122.3
GPT-6 Astramax121.3
GPT-6.1 Solmax119.2
Muse Wonder Fullmax118.3
Claude Opus 5max117.2
Muse Wondermax113.4
Kimi K3.1 Promax112.9
Claude Fable 5max112.5
GPT-6 Solmax110.6
GPT-5.6 Solmax108.7
Muse Spark 1.3max107.4
Gemini 3.7 Flashhigh107.1
DeepSeek V4.1 Flash 1017max106.6
Gemini 3.8 Flashhigh106.5
GPT-6.1 Terramax105.2
Claude Haiku 5.5max103.4

Popularity compared

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

Gemini 4 Argon is more popular than Claude Haiku 5.5: 92 to 77 out of 100.

Over time

Weekly values from October 18, 2026 to November 5, 2026

Claude Haiku 5.5Gemini 4 Argon

All data side by side

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

MetricClaude Haiku 5.5Gemini 4 Argon
Intelligence
Overall indexpoints, 100 = reference group average, higher is better103.4122.3
RankRank 20 of 91Rank 5 of 91
Price per 1M tokens
Inputwhat you send$0.10above 100,000 tokens: $0.50$2
Outputwhat the model writes$0.50above 100,000 tokens: $2.50$10
Speed
Tokens per second23674
Popularity
Popularitysearch, usage and mentions, 0 to 10077Rank 3 of 87592Rank 1 of 875
Technical
Context windowhow much text the model reads at once1 M tokens≈ 1,500 A4 pages1.05 M tokens≈ 1,570 A4 pages
Knowledge cutoffJune 2026n/a
ReleasedOct 7, 2026Oct 13, 2026
AvailabilityActiveActive
Open weightsnono
  • 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 125.7, rank 2. No API price in our data yet.

Haiku 5.5 vs. Gemini 4 Carbon
Best model in the overall indexClaude Opus 5.5

Overall index 126.1, rank 1. $4 input and $20 output per 1M tokens.

Gemini 4 Argon vs. Claude Opus 5.5

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: Claude Haiku 5.5B: Gemini 4 Argon

AA-BriefcaseOverall · higher is betterClaude Haiku 5.5: 1,441.38 eloGemini 4 Argon: 1,485.03 eloArtificial AnalysisAs of 11/06/2026
AA-OmniscienceOverall · higher is betterClaude Haiku 5.5: 5.3 pointsGemini 4 Argon: 46.1 pointsArtificial AnalysisAs of 11/06/2026
AA-Omniscience AccuracyOverall · higher is betterClaude Haiku 5.5: 31.8%Gemini 4 Argon: 48.3%Artificial AnalysisAs of 11/06/2026
AA-Omniscience Hallucination RateOverall · lower is betterClaude Haiku 5.5: 38.9%Gemini 4 Argon: 4.3%Artificial AnalysisAs of 11/06/2026
AutomationBench-AAOverall · higher is betterClaude Haiku 5.5: 33.7%Gemini 4 Argon: 77.5%Artificial AnalysisAs of 11/06/2026
BioMysteryBenchOverall · higher is betterTest setup not documented as identicalClaude Haiku 5.5: 70.4%Gemini 4 Argon: 76.3%Vals AIAs of 11/05/2026
Code MigrationOverall · higher is betterTest setup not documented as identicalClaude Haiku 5.5: 44.6%Gemini 4 Argon: 68.2%Vals AIAs of 10/29/2026
Code Migration v1.1Overall · higher is betterTest setup not documented as identicalClaude Haiku 5.5: 52.4%Gemini 4 Argon: 70.8%Vals AIAs of 10/30/2026
CritPt v2 (Hard Subset)Overall · higher is betterClaude Haiku 5.5: 45.0%Gemini 4 Argon: 52.5%Artificial AnalysisAs of 11/06/2026
CyberBench v1.1Overall · higher is betterTest setup not documented as identicalClaude Haiku 5.5: 75.5%Gemini 4 Argon: 77.9%Vals AIAs of 11/05/2026
Show 54 more benchmarks
EMBOverall · higher is betterTest setup not documented as identicalClaude Haiku 5.5: 59%Gemini 4 Argon: 75.2%Vals AIAs of 10/20/2026
EMB v1.1Overall · higher is betterTest setup not documented as identicalClaude Haiku 5.5: 65.5%Gemini 4 Argon: 74.8%Vals AIAs of 11/05/2026
Finance Agent (v2)Overall · higher is betterTest setup not documented as identicalClaude Haiku 5.5: 54.1%Gemini 4 Argon: 65.4%Vals AIAs of 10/29/2026
Finance Agent v2.1Overall · higher is betterTest setup not documented as identicalClaude Haiku 5.5: 65.4%Gemini 4 Argon: 67.7%Vals AIAs of 11/05/2026
FrontierCodeOverall · higher is betterClaude Haiku 5.5: 23.2%Gemini 4 Argon: 25.7%Artificial AnalysisAs of 11/06/2026
FrontierCode 1.1 MainOverall · higher is betterClaude Haiku 5.5: 43.6%Gemini 4 Argon: 43.5%Artificial AnalysisAs of 11/06/2026
GDP.pdfOverall · higher is betterClaude Haiku 5.5: 17.2%Gemini 4 Argon: 21.8%Artificial AnalysisAs of 11/06/2026
GDPval-AAOverall · higher is betterClaude Haiku 5.5: 1,424.29 eloGemini 4 Argon: 1,630.66 eloArtificial AnalysisAs of 11/06/2026
HLAB-Vals-1.1Overall · Task fully resolved · higher is betterTest setup not documented as identicalClaude Haiku 5.5: 4.2%Gemini 4 Argon: 27.1%Vals AIAs of 11/05/2026
HLE-DiamondOverall · higher is betterClaude Haiku 5.5: 23.7%Gemini 4 Argon: 56.7%Artificial AnalysisAs of 11/06/2026
ImmigrationOverall · higher is betterTest setup not documented as identicalClaude Haiku 5.5: 61.8%Gemini 4 Argon: 68.1%Vals AIAs of 10/28/2026
IOIOverall · higher is betterTest setup not documented as identicalClaude Haiku 5.5: 47.3%Gemini 4 Argon: 100%Vals AIAs of 10/29/2026
Legal Research BenchOverall · All-pass · higher is betterTest setup not documented as identicalClaude Haiku 5.5: 43.8%Gemini 4 Argon: 54.8%Vals AIAs of 11/05/2026
LMArena Code Arena WebDevOverall · higher is betterClaude Haiku 5.5: 1,589Gemini 4 Argon: 1,679LMArenaAs of 10/28/2026
LMArena Text, Style ControlOverall · higher is betterClaude Haiku 5.5: 1,425Gemini 4 Argon: 1,520LMArenaAs of 10/28/2026
MedCodeOverall · higher is betterTest setup not documented as identicalClaude Haiku 5.5: 51.5%Gemini 4 Argon: 58.8%Vals AIAs of 10/29/2026
MedScribeOverall · higher is betterTest setup not documented as identicalClaude Haiku 5.5: 89.5%Gemini 4 Argon: 87.4%Vals AIAs of 10/29/2026
MysteryMechanismOverall · higher is betterTest setup not documented as identicalClaude Haiku 5.5: 35.1%Gemini 4 Argon: 45.5%Vals AIAs of 10/29/2026
ProgramBenchOverall · higher is betterTest setup not documented as identicalClaude Haiku 5.5: 2.5%Gemini 4 Argon: 2.5%Vals AIAs of 11/05/2026
ProofBench v1.1Overall · higher is betterTest setup not documented as identicalClaude Haiku 5.5: 89%Gemini 4 Argon: 99%Vals AIAs of 10/29/2026
Public Benefits Bench v1.1Overall · higher is betterTest setup not documented as identicalClaude Haiku 5.5: 63.2%Gemini 4 Argon: 69.8%Vals AIAs of 10/12/2026
SAGEOverall · higher is betterTest setup not documented as identicalClaude Haiku 5.5: 89.8%Gemini 4 Argon: 89.5%Vals AIAs of 11/05/2026
SRE BenchOverall · higher is betterTest setup not documented as identicalClaude Haiku 5.5: 5.7%Gemini 4 Argon: 44.3%Vals AIAs of 11/05/2026
SWE-bench MultimodalOverall · higher is betterTest setup not documented as identicalClaude Haiku 5.5: 44%Gemini 4 Argon: 56%Vals AIAs of 11/05/2026
Tax Agent BenchOverall · higher is betterTest setup not documented as identicalClaude Haiku 5.5: 31.9%Gemini 4 Argon: 44.6%Vals AIAs of 11/05/2026
Terminal-BenchOverall · higher is betterClaude Haiku 5.5: 21.7%Gemini 4 Argon: 57.1%Artificial AnalysisAs of 11/06/2026
Terminal-Bench 4.0Overall · higher is betterTest setup not documented as identicalClaude Haiku 5.5: 36.4%Gemini 4 Argon: 57.6%Vals AIAs of 11/05/2026
Terminal-Bench-ScienceOverall · higher is betterTest setup not documented as identicalClaude Haiku 5.5: 10%Gemini 4 Argon: 44.3%Vals AIAs of 11/05/2026
Terminal-Bench-ScienceOverall · higher is betterClaude Haiku 5.5: 10.0%Gemini 4 Argon: 52.9%Artificial AnalysisAs of 11/06/2026
Vals Finance IndexOverall · higher is betterTest setup not documented as identicalClaude Haiku 5.5: 57.4%Gemini 4 Argon: 64.9%Vals AIAs of 11/05/2026
Vals IndexOverall · higher is betterTest setup not documented as identicalClaude Haiku 5.5: 58.7%Gemini 4 Argon: 69.2%Vals AIAs of 11/05/2026
Vals Legal IndexOverall · higher is betterTest setup not documented as identicalClaude Haiku 5.5: 70.3%Gemini 4 Argon: 76.7%Vals AIAs of 11/05/2026
Vals Router IndexFull Index · higher is betterClaude Haiku 5.5: 58.7%Gemini 4 Argon: 69.2%Vals AIAs of 11/03/2026
Vals Science IndexOverall · higher is betterTest setup not documented as identicalClaude Haiku 5.5: 38.5%Gemini 4 Argon: 55.4%Vals AIAs of 10/25/2026
Vibe Code Bench 1-100Overall · higher is betterTest setup not documented as identicalClaude Haiku 5.5: 20.4%Gemini 4 Argon: 21.2%Vals AIAs of 10/29/2026
Vibe Code Bench v1.1Overall · higher is betterTest setup not documented as identicalClaude Haiku 5.5: 90.4%Gemini 4 Argon: 91.9%Vals AIAs of 11/05/2026
BioMysteryBenchHard · higher is betterTest setup not documented as identicalClaude Haiku 5.5: 29.4%Gemini 4 Argon: 39.2%Vals AIAs of 11/05/2026
Code MigrationCLI · higher is betterTest setup not documented as identicalClaude Haiku 5.5: 36.1%Gemini 4 Argon: 67.6%Vals AIAs of 10/29/2026
Code Migration v1.1CLI · higher is betterTest setup not documented as identicalClaude Haiku 5.5: 42.1%Gemini 4 Argon: 67.8%Vals AIAs of 10/30/2026
CyberBench v1.1Patch · higher is betterTest setup not documented as identicalClaude Haiku 5.5: 89.3%Gemini 4 Argon: 85.7%Vals AIAs of 11/05/2026
EMBComps · higher is betterTest setup not documented as identicalClaude Haiku 5.5: 77.9%Gemini 4 Argon: 83%Vals AIAs of 10/20/2026
EMB v1.1Comps · higher is betterTest setup not documented as identicalClaude Haiku 5.5: 77.7%Gemini 4 Argon: 82.9%Vals AIAs of 11/05/2026
Finance Agent (v2)Adjustments · higher is betterTest setup not documented as identicalClaude Haiku 5.5: 49.6%Gemini 4 Argon: 60.5%Vals AIAs of 10/29/2026
Finance Agent v2.1Adjustments · higher is betterTest setup not documented as identicalClaude Haiku 5.5: 67.7%Gemini 4 Argon: 70.8%Vals AIAs of 11/05/2026
HLAB-Vals-1.1Antitrust Competition · Criteria passed · higher is betterTest setup not documented as identicalClaude Haiku 5.5: 86.2%Gemini 4 Argon: 97.6%Vals AIAs of 11/05/2026
ImmigrationAll-Pass · higher is betterTest setup not documented as identicalClaude Haiku 5.5: 16%Gemini 4 Argon: 20.6%Vals AIAs of 10/28/2026
IOIIOI 2024 · higher is betterTest setup not documented as identicalClaude Haiku 5.5: 67.7%Gemini 4 Argon: 100%Vals AIAs of 10/29/2026
Legal Research BenchAdministrative / Regulatory · All-pass · higher is betterTest setup not documented as identicalClaude Haiku 5.5: 50%Gemini 4 Argon: 68.2%Vals AIAs of 11/05/2026
LMArena Code Arena WebDevHTML development · higher is betterClaude Haiku 5.5: 1,568Gemini 4 Argon: 1,667LMArenaAs of 10/28/2026
LMArena Text, Style ControlBusiness, management and finance · higher is betterClaude Haiku 5.5: 1,435Gemini 4 Argon: 1,512LMArenaAs of 10/28/2026
ProgramBenchAlmost Resolved · higher is betterTest setup not documented as identicalClaude Haiku 5.5: 29.5%Gemini 4 Argon: 41%Vals AIAs of 11/05/2026
SAGEComputer Science · higher is betterTest setup not documented as identicalClaude Haiku 5.5: 91.6%Gemini 4 Argon: 95%Vals AIAs of 11/05/2026
SRE BenchCapability Score · higher is betterTest setup not documented as identicalClaude Haiku 5.5: 18.1%Gemini 4 Argon: 57.8%Vals AIAs of 11/05/2026
SWE-bench Multimodalbpmn-js · higher is betterTest setup not documented as identicalClaude Haiku 5.5: 64.2%Gemini 4 Argon: 71.7%Vals AIAs of 11/05/2026

More comparisons

Compare Claude Haiku 5.5 and Gemini 4 Argon with the models people compare them with most often.

Compare another matchup

The most popular comparisons

  1. 1Claude Opus 5.5 vs. Gemini 4 Argon
  2. 2Claude Haiku 5.5 vs. GPT-6 Luna
  3. 3Claude Sonnet 5.5 vs. Claude Haiku 5.5
  4. 4Claude Haiku 5.5 vs. DeepSeek V4.1 Flash 1017
  5. 5Claude Haiku 5.5 vs. DeepSeek-V4-Flash
  6. 6GPT-6 Astra vs. Gemini 4 Argon
  7. 7Claude Haiku 5.5 vs. DeepSeek-V4.1-Flash
  8. 8Claude Fable 5.1 vs. Gemini 4 Argon
  9. 9Claude Opus 5.5 vs. Claude Haiku 5.5
Show all 48 comparisons
  1. 10GPT-6 Sol vs. Gemini 4 Argon
  2. 11GPT-6.1 Terra vs. Gemini 4 Argon
  3. 12Claude Haiku 5.5 vs. GLM-5.3
  4. 13Claude Haiku 5.5 vs. Gemini 3.5 Flash-Lite
  5. 14Claude Haiku 5.5 vs. Gemini 3.8 Flash
  6. 15Claude Haiku 5.5 vs. Claude Sonnet 4.5
  7. 16GPT-6.1 Sol vs. Gemini 4 Argon
  8. 17Claude Haiku 5.5 vs. Claude Sonnet 5
  9. 18Gemini 4 Argon vs. DeepSeek-V4-Flash
  10. 19Claude Haiku 5.5 vs. Claude Opus 5
  11. 20Claude Haiku 5.5 vs. GPT-6 Astra
  12. 21Claude Haiku 5.5 vs. Gemini 3.5 Flash
  13. 22Claude Haiku 5.5 vs. Claude Opus 4.8
  14. 23Gemini 4 Argon vs. Kimi K3.1 Pro
  15. 24Gemini 4 Argon vs. Grok 4.7
  16. 25Claude Haiku 5.5 vs. Grok 4.7
  17. 26Claude Haiku 5.5 vs. GPT-5.6 Luna
  18. 27Claude Haiku 5.5 vs. Qwen 3.8 Max 0902
  19. 28Claude Sonnet 5.5 vs. Gemini 4 Argon
  20. 29Claude Haiku 5.5 vs. Muse Spark 1.3
  21. 30Gemini 4 Argon vs. DeepSeek V4.1 Flash 1017
  22. 31Claude Haiku 5.5 vs. Claude Sonnet 4.6
  23. 32Claude Haiku 5.5 vs. Gemini 3.7 Flash
  24. 33Claude Haiku 5.5 vs. Mistral Large 4
  25. 34GPT-5.6 Sol vs. Gemini 4 Argon
  26. 35Gemini 4 Argon vs. DeepSeek-V4-Pro
  27. 36Claude Haiku 5.5 vs. GPT-6.1 Sol
  28. 37Gemini 4 Argon vs. Gemini 3.1 Pro Preview
  29. 38Claude Haiku 5.5 vs. Gemini 3.1 Pro Preview
  30. 39Claude Haiku 5.5 vs. GLM-5.3-Flash
  31. 40Claude Haiku 5.5 vs. DeepSeek-V4-Pro
  32. 41Claude Haiku 5.5 vs. GPT-5.6 Sol
  33. 42Claude Haiku 5.5 vs. Gemini 3.6 Flash
  34. 43Claude Haiku 5.5 vs. Claude Opus 4.6
  35. 44Claude Haiku 5.5 vs. Kimi K2.6
  36. 45Claude Haiku 5.5 vs. Claude Opus 4.7
  37. 46Claude Haiku 5.5 vs. Mistral Large 3
  38. 47Claude Haiku 5.5 vs. GPT-5.5
  39. 48Claude Haiku 5.5 vs. GPT-6.1 Terra