Skip to main content

Head-to-head comparison

Claude Sonnet 4.5 vs. Gemini 4 Argon

Compare published benchmark results from matching versions and cohorts, API pricing, and technical specifications. Any documented test setup differences remain visible.

shared result series
7
distinct benchmark metrics
3
latest retrieval
2026-10-16

Change model selection

Specifications

General specifications

Release date, availability, context window, architecture, and published parameter counts at a glance. Undisclosed details remain marked as unavailable.

Specifications for Claude Sonnet 4.5 and Gemini 4 Argon
AttributeClaude Sonnet 4.5Gemini 4 Argon
ProviderAnthropicGoogle DeepMind
ReleasedSep 2025Oct 13, 2026
AvailabilityActiveActive
Model typeProprietaryProprietary
ParametersNot publishedNot published
ArchitectureNot publishedNot published
Context window200,000 tokens1,048,576 tokens shared across input, thinking, and output
Knowledge cutoffJanuary 2025Not published
Technical sourcesModel, ContextModel

Pricing

API pricing compared

The table compares official standard API rates per 1M tokens, including published cache pricing. Batch, fast, priority, regional surcharges, tool calls, and cloud platform pricing are excluded.

API pricing for Claude Sonnet 4.5 and Gemini 4 Argon
Price typeClaude Sonnet 4.5Gemini 4 Argon
API input$3$2
API output$15$10
Cache read$0.3$0.1
Cache write (5 min.)$3.75Not listed
Cache write (1 hr.)$6Not listed
Price verified09/22/2026 Source10/25/2026 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

Claude Sonnet 4.5Gemini 4 Argon
API inputUSD per 1M tokens, base tier
Claude Sonnet 4.5$3
Gemini 4 ArgonLower price$2
API outputUSD per 1M tokens, base tier
Claude Sonnet 4.5$15
Gemini 4 ArgonLower price$10
Cache readUSD per 1M tokens, base tier
Claude Sonnet 4.5$0.3
Gemini 4 ArgonLower price$0.1

Key to the marks:better valuebetter, but not conclusivetie

Pricing by provider

Direct developer pricing and provider endpoint tariffs routed through OpenRouter are listed separately. Prices are in USD per 1M tokens. Context-dependent direct tiers plus regional, Flex, Priority, and other OpenRouter tariffs remain individually identifiable.

No provider tariff for Gemini 4 Argon is available in the stored OpenRouter snapshot. The official direct price is still shown.

Provider pricing for Claude Sonnet 4.5 and Gemini 4 Argon
ModelProviderPurchase route and tariffInput per 1M tokensOutput per 1M tokensSource
Claude Sonnet 4.5AnthropicDirect from developerStandard APILowest listed price: $3Lowest listed price: $15Source09/22/2026
Amazon BedrockVia OpenRouteramazon-bedrockLowest listed price: $3Lowest listed price: $15Source10/26/2026
Amazon BedrockVia OpenRouteramazon-bedrock/eu-west-1$3.3$16.5Source10/26/2026
AnthropicVia OpenRouteranthropicLowest listed price: $3Lowest listed price: $15Source10/26/2026
AzureVia OpenRouterazure/globalLowest listed price: $3Lowest listed price: $15Source10/26/2026
Claude Platform on AWSVia OpenRouterclaude-on-awsLowest listed price: $3Lowest listed price: $15Source10/26/2026
GoogleVia OpenRoutergoogle-vertex/globalLowest listed price: $3Lowest listed price: $15Source10/26/2026
GoogleVia OpenRoutergoogle-vertex/us-east5$3.3$16.5Source10/26/2026
Gemini 4 ArgonGoogle DeepMindDirect from developerStandard APILowest listed price: $2Lowest listed price: $10Source10/25/2026

Benchmark index

Benchmark index compared

The index combines independent benchmarks on a scale from 0 to 100. A lead only counts when a model comes first in at least 95% of 200 recalculations with randomly redrawn test families. Otherwise both count as level.

Open the AI leaderboard
Claude Sonnet 4.5

Overall index

No overall score yet

Gemini 4 Argon

Overall index

92.6

Gemini 4 Argon leads in 4 of 4 shared areas.

AreaClaude Sonnet 4.5Gemini 4 Argon
Finance7.794.6
Legal7.994.9
Health16.992.8
Education4.693.6

Performance

Shared benchmarks

Only published results with the same benchmark version, task, metric, and comparison cohort are paired. Different reasoning levels, agents, harnesses, or output limits appear directly in the table.

Capability profile from matched benchmarks

Each axis averages directly matched benchmark families. A value of 100 means the stronger value within this pair, not a universal quality score.

Not enough directly matched categories for a reliable radar

Only 0 of at least 5 categories have comparable, direct model measurements. The benchmark tables below show the available evidence without filling missing axes.

Claude Sonnet 4.5Gemini 4 Argon
MedCodeOverall. Higher is better. Test setup not documented as identical
Claude Sonnet 4.540.569 %
Gemini 4 ArgonHigher measured value58.801 %
MedScribeOverall. Higher is better. Test setup not documented as identical
Claude Sonnet 4.584.515 %
Gemini 4 ArgonHigher measured value87.427 %
SAGEOverall. Higher is better. Test setup not documented as identical
Claude Sonnet 4.532.88 %
Gemini 4 ArgonHigher measured value53.645 %
SAGEAutomata. Higher is better. Test setup not documented as identical
Claude Sonnet 4.520.238 %
Gemini 4 ArgonHigher measured value45.635 %
SAGECalculus. Higher is better. Test setup not documented as identical
Claude Sonnet 4.537.654 %
Gemini 4 ArgonHigher measured value84.877 %
SAGELinear Algebra. Higher is better. Test setup not documented as identical
Claude Sonnet 4.551.417 %
Gemini 4 ArgonHigher measured value74.031 %
SAGEPartial Differential Equations. Higher is better. Test setup not documented as identical
Claude Sonnet 4.526.984 %
Gemini 4 ArgonHigher measured value41.27 %

Key to the marks:better valuebetter, but not conclusivetie

Benchmark scores for Claude Sonnet 4.5 and Gemini 4 Argon
Benchmark and taskClaude Sonnet 4.5Gemini 4 ArgonSource
MedCodeOverall
Test details
Test setup not documented as identicalNo direct winnerVersion: 1Metric: accuracyScoring: Higher is betterClaude Sonnet 4.5: Snapshot: claude-sonnet-4-5-20250929, Temperature: 1, Output limit: 30,000 tokens
Gemini 4 Argon: Reasoning: high, Temperature: 1, Output limit: 262,144 tokens
40.569 %
Higher measured value58.801 %
Vals AI
Source details
Data as of: 10/13/2026
MedScribeOverall
Test details
Test setup not documented as identicalNo direct winnerVersion: 1Metric: accuracyScoring: Higher is betterClaude Sonnet 4.5: Snapshot: claude-sonnet-4-5-20250929, Temperature: 1, Output limit: 30,000 tokens
Gemini 4 Argon: Reasoning: high, Temperature: 1, Output limit: 262,144 tokens
84.515 %
Higher measured value87.427 %
Vals AI
Source details
Data as of: 10/13/2026
SAGEOverall
Test details
Test setup not documented as identicalNo direct winnerVersion: 1Metric: accuracyScoring: Higher is betterClaude Sonnet 4.5: Snapshot: claude-sonnet-4-5-20250929, Temperature: 1, Output limit: 30,000 tokens
Gemini 4 Argon: Reasoning: high, Temperature: 1, Output limit: 262,144 tokens
32.88 %
Higher measured value53.645 %
Vals AI
Source details
Data as of: 10/08/2026
SAGEAutomata
Test details
Test setup not documented as identicalNo direct winnerVersion: 1Metric: accuracyScoring: Higher is betterClaude Sonnet 4.5: Snapshot: claude-sonnet-4-5-20250929, Temperature: 1, Output limit: 30,000 tokens
Gemini 4 Argon: Reasoning: high, Temperature: 1, Output limit: 262,144 tokens
20.238 %
Higher measured value45.635 %
Vals AI
Source details
Data as of: 10/08/2026
SAGECalculus
Test details
Test setup not documented as identicalNo direct winnerVersion: 1Metric: accuracyScoring: Higher is betterClaude Sonnet 4.5: Snapshot: claude-sonnet-4-5-20250929, Temperature: 1, Output limit: 30,000 tokens
Gemini 4 Argon: Reasoning: high, Temperature: 1, Output limit: 262,144 tokens
37.654 %
Higher measured value84.877 %
Vals AI
Source details
Data as of: 10/08/2026
SAGELinear Algebra
Test details
Test setup not documented as identicalNo direct winnerVersion: 1Metric: accuracyScoring: Higher is betterClaude Sonnet 4.5: Snapshot: claude-sonnet-4-5-20250929, Temperature: 1, Output limit: 30,000 tokens
Gemini 4 Argon: Reasoning: high, Temperature: 1, Output limit: 262,144 tokens
51.417 %
Higher measured value74.031 %
Vals AI
Source details
Data as of: 10/08/2026
SAGEPartial Differential Equations
Test details
Test setup not documented as identicalNo direct winnerVersion: 1Metric: accuracyScoring: Higher is betterClaude Sonnet 4.5: Snapshot: claude-sonnet-4-5-20250929, Temperature: 1, Output limit: 30,000 tokens
Gemini 4 Argon: Reasoning: high, Temperature: 1, Output limit: 262,144 tokens
26.984 %
Higher measured value41.27 %
Vals AI
Source details
Data as of: 10/08/2026

Key to the marks:better valuebetter, but not conclusivetie

Our model tests

Our tests

SVG short test

One SVG prompt and fixed output settings. Captures are shown only with 0 reported reasoning tokens or documented lack of reasoning controls. Identical test conditions do not make the models' internal compute identical.

Shared test round: 43b8c5c46830

Claude Sonnet 4.5

Claude Sonnet 4.5: SVG short test
API reports 0 reasoning tokensTest run: Oct 14, 2026Provider: anthropicAPI model: anthropic/claude-sonnet-4.5686 output tokens

Gemini 4 Argon

Unavailable in this round

Earlier tests

Pelican on a bicycle

A community classic for free-form SVG drawing.

Claude Sonnet 4.5

Claude Sonnet 4.5: Pelican on a bicycle
A community classic for free-form SVG drawing.

Reasoning (requested): high

Current attempt
Run date
Oct 1, 2026
API provider
openrouter
Requested API model
anthropic/claude-sonnet-4.5
API model reported in response
anthropic/claude-sonnet-4.5
Reasoning setting
high
Pinned endpoint
Anthropic | anthropic/claude-4.5-sonnet-20250929
Temperature
Provider default
Token limit including reasoning
8,192 tokens
Test protocol
community-visual-tests-v1
Technical checks
Passed, not a quality rating
Response time
30.2 s

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

Gemini 4 Argon

Not tested yet

Prompt and test conditions

Generate an SVG of a pelican riding a bicycle

Token limit including reasoning: 8,192 tokens

Task origin (Simon Willison)

How to read this comparison

Winning one benchmark is not an overall verdict

Your workload, budget, and required context length matter most. A coding benchmark says little about visual understanding or agent performance.

The standard price table uses direct developer rates. The provider comparison labels OpenRouter endpoints, regions, and special tariffs separately.

Every result links to its measurement source and retrieval date. Labels distinguish vendor reports, official benchmark leaderboards, and independent evaluations. Disputed or archived results are excluded.

More matchups

Related LLM comparisons

Compare Claude Sonnet 4.5 and Gemini 4 Argon with other leading models using the same data and benchmark logic.

View the complete LLM comparison