Skip to main content

Head-to-head comparison

Claude Sonnet 4.5 vs. Gemini 3.8 Flash

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 3.8 Flash
AttributeClaude Sonnet 4.5Gemini 3.8 Flash
ProviderAnthropicGoogle
ReleasedSep 2025Sep 2, 2026
AvailabilityActiveActive
Model typeProprietaryProprietary
ParametersNot publishedNot published
ArchitectureNot publishedNot published
Context window200,000 tokens1,048,576 tokens
Knowledge cutoffJanuary 2025March 2026
Technical sourcesModel, ContextModel, Knowledge cutoff

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 3.8 Flash
Price typeClaude Sonnet 4.5Gemini 3.8 Flash
API input$3$0.75
API output$15$3.75
Cache read$0.3$0.075
Cache write (5 min.)$3.75Not listed
Cache write (1 hr.)$6Not listed
Price verified09/22/2026 Source09/22/2026 Source
Claude Sonnet 4.5Gemini 3.8 Flash
API inputUSD per 1M tokens, base tier
Claude Sonnet 4.5$3
Gemini 3.8 FlashLower price$0.75
API outputUSD per 1M tokens, base tier
Claude Sonnet 4.5$15
Gemini 3.8 FlashLower price$3.75
Cache readUSD per 1M tokens, base tier
Claude Sonnet 4.5$0.3
Gemini 3.8 FlashLower price$0.075

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.

Provider pricing for Claude Sonnet 4.5 and Gemini 3.8 Flash
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 3.8 FlashGoogleDirect from developerStandard API$0.75$3.75Source09/22/2026
GoogleVia OpenRoutergoogle-vertex/global$0.75$3.75Source10/26/2026
GoogleVia OpenRoutergoogle-vertex/global/priority$1.35$6.75Source10/26/2026
Google AI StudioVia OpenRoutergoogle-ai-studio$0.75$3.75Source10/26/2026
Google AI StudioVia OpenRoutergoogle-ai-studio/flexLowest listed price: $0.375Lowest listed price: $1.875Source10/26/2026
Google AI StudioVia OpenRoutergoogle-ai-studio/priority$1.35$6.75Source10/26/2026

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 3.8 Flash

Overall index

66.9

Gemini 3.8 Flash leads in 4 of 4 shared areas.

AreaClaude Sonnet 4.5Gemini 3.8 Flash
Finance7.772.4
Legal7.970.3
Health16.956.8
Education4.639.8

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 3.8 Flash
MedCodeOverall. Higher is better. Test setup not documented as identical
Claude Sonnet 4.540.569 %
Gemini 3.8 FlashHigher measured value48.135 %
MedScribeOverall. Higher is better. Test setup not documented as identical
Claude Sonnet 4.5Higher measured value84.515 %
Gemini 3.8 Flash84.496 %
SAGEOverall. Higher is better. Test setup not documented as identical
Claude Sonnet 4.532.88 %
Gemini 3.8 FlashHigher measured value35.064 %
SAGEAutomata. Higher is better. Test setup not documented as identical
Claude Sonnet 4.520.238 %
Gemini 3.8 FlashHigher measured value33.334 %
SAGECalculus. Higher is better. Test setup not documented as identical
Claude Sonnet 4.537.654 %
Gemini 3.8 FlashHigher measured value79.63 %
SAGELinear Algebra. Higher is better. Test setup not documented as identical
Claude Sonnet 4.5Higher measured value51.417 %
Gemini 3.8 Flash41.7 %
SAGEPartial Differential Equations. Higher is better. Test setup not documented as identical
Claude Sonnet 4.526.984 %
Gemini 3.8 FlashHigher measured value30.159 %

Key to the marks:better valuebetter, but not conclusivetie

Benchmark scores for Claude Sonnet 4.5 and Gemini 3.8 Flash
Benchmark and taskClaude Sonnet 4.5Gemini 3.8 FlashSource
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 3.8 Flash: Reasoning: high, Temperature: 1, Output limit: 65,536 tokens
40.569 %
Higher measured value48.135 %
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 3.8 Flash: Reasoning: high, Temperature: 1, Output limit: 65,536 tokens
Higher measured value84.515 %
84.496 %
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 3.8 Flash: Reasoning: high, Temperature: 1, Output limit: 30,000 tokens
32.88 %
Higher measured value35.064 %
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 3.8 Flash: Reasoning: high, Temperature: 1, Output limit: 30,000 tokens
20.238 %
Higher measured value33.334 %
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 3.8 Flash: Reasoning: high, Temperature: 1, Output limit: 30,000 tokens
37.654 %
Higher measured value79.63 %
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 3.8 Flash: Reasoning: high, Temperature: 1, Output limit: 30,000 tokens
Higher measured value51.417 %
41.7 %
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 3.8 Flash: Reasoning: high, Temperature: 1, Output limit: 30,000 tokens
26.984 %
Higher measured value30.159 %
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 3.8 Flash

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 3.8 Flash

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

Reasoning (requested): high

Current attempt
Run date
Oct 5, 2026
API provider
openrouter
Requested API model
google/gemini-3.8-flash
API model reported in response
google/gemini-3.8-flash
Reasoning setting
high
Pinned endpoint
Google AI Studio | google/gemini-3.8-flash-20260902
Temperature
Provider default
Token limit including reasoning
8,192 tokens
Test protocol
community-visual-tests-v1
Technical checks
Failed
Response time
40.2 s

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

Earlier attempts (3)
  • Oct 2, 2026API request failedReasoning setting: high
  • Oct 1, 2026API request failedReasoning setting: high
  • Sep 7, 2026API request failedReasoning setting: high
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 3.8 Flash with other leading models using the same data and benchmark logic.

View the complete LLM comparison