Head-to-head comparison

Claude Haiku 4.5 vs. Gemini 3.5 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: 5
distinct benchmark metrics: 2
latest retrieval: 2026-10-16

First modelSecond model

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 Haiku 4.5 and Gemini 3.5 Flash
Attribute	Claude Haiku 4.5	Gemini 3.5 Flash
Provider	Anthropic	Google
Released	Oct 2025	May 19, 2026
Availability	Active	Active
Model type	Proprietary	Proprietary
Parameters	Not published	Not published
Architecture	Not published	Not published
Context window	200,000 tokens	1,048,576 tokens
Knowledge cutoff	February 2025	Not published
Technical sources	Model	Model

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 Haiku 4.5 and Gemini 3.5 Flash
Price type	Claude Haiku 4.5	Gemini 3.5 Flash
API input	$1	$1.5
API output	$5	$9
Cache read	$0.1	$0.15
Cache write (5 min.)	$1.25	Not listed
Cache write (1 hr.)	$2	Not listed
Price verified	09/22/2026 Source	09/22/2026 Source

Claude Haiku 4.5Gemini 3.5 Flash

API inputUSD per 1M tokens, base tier

Claude Haiku 4.5$1

Gemini 3.5 Flash$1.5

API outputUSD per 1M tokens, base tier

Claude Haiku 4.5$5

Gemini 3.5 Flash$9

Cache readUSD per 1M tokens, base tier

Claude Haiku 4.5$0.1

Gemini 3.5 Flash$0.15

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 Haiku 4.5 and Gemini 3.5 Flash
Model	Provider	Purchase route and tariff	Input per 1M tokens	Output per 1M tokens	Source
Claude Haiku 4.5	Anthropic	Direct from developerStandard API	Lowest listed price: $1	Lowest listed price: $5	Source09/22/2026
	Amazon Bedrock	Via OpenRouteramazon-bedrock/eu-west-1	$1.1	$5.5	Source10/26/2026
	Amazon Bedrock	Via OpenRouteramazon-bedrock/global	Lowest listed price: $1	Lowest listed price: $5	Source10/26/2026
	Amazon Bedrock	Via OpenRouteramazon-bedrock/us	$1.1	$5.5	Source10/26/2026
	Anthropic	Via OpenRouteranthropic	Lowest listed price: $1	Lowest listed price: $5	Source10/26/2026
	Azure	Via OpenRouterazure/global	Lowest listed price: $1	Lowest listed price: $5	Source10/26/2026
	Google	Via OpenRoutergoogle-vertex/europe	$1.1	$5.5	Source10/26/2026
	Google	Via OpenRoutergoogle-vertex/global	Lowest listed price: $1	Lowest listed price: $5	Source10/26/2026
	Google	Via OpenRoutergoogle-vertex/us-east5	$1.1	$5.5	Source10/26/2026
Gemini 3.5 Flash	Google	Direct from developerStandard API	$1.5	$9	Source09/22/2026
	Google	Via OpenRoutergoogle-vertex/global	$1.5	$9	Source10/26/2026
	Google	Via OpenRoutergoogle-vertex/global/flex	Lowest listed price: $0.75	Lowest listed price: $4.5	Source10/26/2026
	Google	Via OpenRoutergoogle-vertex/global/priority	$2.7	$16.2	Source10/26/2026
	Google	Via OpenRoutergoogle-vertex/us	$1.65	$9.9	Source10/26/2026
	Google AI Studio	Via OpenRoutergoogle-ai-studio	$1.5	$9	Source10/26/2026
	Google AI Studio	Via OpenRoutergoogle-ai-studio/flex	Lowest listed price: $0.75	Lowest listed price: $4.5	Source10/26/2026
	Google AI Studio	Via OpenRoutergoogle-ai-studio/priority	$2.7	$16.2	Source10/26/2026

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 Haiku 4.5

Overall index

No overall score yet

Gemini 3.5 Flash

Overall index

43.4

Gemini 3.5 Flash leads in 2 of 2 shared areas.

Area	Claude Haiku 4.5	Gemini 3.5 Flash
Finance	3.4	48.3
Productivity	6.2	31.0

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 Haiku 4.5Gemini 3.5 Flash

CorpFin v2Overall. Higher is better. Test setup not documented as identical

Claude Haiku 4.560.295 %

Gemini 3.5 Flash64.686 %

Public Benefits Bench v1.1Overall. Higher is better. Test setup not documented as identical

Claude Haiku 4.554.263 %

Gemini 3.5 Flash59.472 %

CorpFin v2Exact Pages. Higher is better. Test setup not documented as identical

Claude Haiku 4.560.256 %

Gemini 3.5 Flash62.821 %

CorpFin v2Max Fitting Context. Higher is better. Test setup not documented as identical

Claude Haiku 4.558.858 %

Gemini 3.5 Flash66.667 %

CorpFin v2Shared Max Context. Higher is better. Test setup not documented as identical

Claude Haiku 4.561.772 %

Gemini 3.5 Flash64.569 %

Key to the marks:better valuebetter, but not conclusivetie

Benchmark scores for Claude Haiku 4.5 and Gemini 3.5 Flash
Benchmark and task	Claude Haiku 4.5	Gemini 3.5 Flash	Source
CorpFin v2Overall Test details Test setup not documented as identicalNo direct winnerVersion: 2Metric: accuracyScoring: Higher is betterClaude Haiku 4.5: Snapshot: claude-haiku-4-5-20251001, Temperature: 1, Output limit: 64,000 tokens Gemini 3.5 Flash: Reasoning: high, Temperature: 1, Output limit: 65,536 tokens	60.295 %	Higher measured value64.686 %	Vals AI Source details Data as of: 08/12/2026
Public Benefits Bench v1.1Overall Test details Test setup not documented as identicalNo direct winnerVersion: 1.1Metric: accuracyScoring: Higher is betterClaude Haiku 4.5: Snapshot: claude-haiku-4-5-20251001, Temperature: 1, Output limit: 64,000 tokens Gemini 3.5 Flash: Reasoning: high, Temperature: 1, Output limit: 65,536 tokens	54.263 %	Higher measured value59.472 %	Vals AI Source details Data as of: 10/12/2026
CorpFin v2Exact Pages Test details Test setup not documented as identicalNo direct winnerVersion: 2Metric: accuracyScoring: Higher is betterClaude Haiku 4.5: Snapshot: claude-haiku-4-5-20251001, Temperature: 1, Output limit: 64,000 tokens Gemini 3.5 Flash: Reasoning: high, Temperature: 1, Output limit: 65,536 tokens	60.256 %	Higher measured value62.821 %	Vals AI Source details Data as of: 08/12/2026
CorpFin v2Max Fitting Context Test details Test setup not documented as identicalNo direct winnerVersion: 2Metric: accuracyScoring: Higher is betterClaude Haiku 4.5: Snapshot: claude-haiku-4-5-20251001, Temperature: 1, Output limit: 64,000 tokens Gemini 3.5 Flash: Reasoning: high, Temperature: 1, Output limit: 65,536 tokens	58.858 %	Higher measured value66.667 %	Vals AI Source details Data as of: 08/12/2026
CorpFin v2Shared Max Context Test details Test setup not documented as identicalNo direct winnerVersion: 2Metric: accuracyScoring: Higher is betterClaude Haiku 4.5: Snapshot: claude-haiku-4-5-20251001, Temperature: 1, Output limit: 64,000 tokens Gemini 3.5 Flash: Reasoning: high, Temperature: 1, Output limit: 65,536 tokens	61.772 %	Higher measured value64.569 %	Vals AI Source details Data as of: 08/12/2026
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 Haiku 4.5

Gemini 3.5 Flash

Unavailable in this round

Earlier tests

Pelican on a bicycle

A community classic for free-form SVG drawing.

Claude Haiku 4.5

Reasoning (requested): high

Current attempt

Run date: Oct 1, 2026
API provider: openrouter
Requested API model: anthropic/claude-haiku-4.5
API model reported in response: anthropic/claude-haiku-4.5
Reasoning setting: high
Pinned endpoint: Anthropic | anthropic/claude-4.5-haiku-20251001
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: 10.1 s

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

Gemini 3.5 Flash

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

Reasoning (requested): high

Current attempt

Run date: Oct 6, 2026
API provider: openrouter
Requested API model: google/gemini-3.5-flash
API model reported in response: google/gemini-3.5-flash
Reasoning setting: high
Pinned endpoint: Google AI Studio | google/gemini-3.5-flash-20260519
Temperature: Provider default
Token limit including reasoning: 8,192 tokens
Test protocol: community-visual-tests-v1
Technical checks: Failed
Response time: 31.7 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

Compare Claude Haiku 4.5 and Gemini 3.5 Flash with other leading models using the same data and benchmark logic.

View the complete LLM comparison

Claude Haiku 4.5 vs. Gemini 3.5 Flash

Change model selection

General specifications

API pricing compared

Benchmark index compared

Shared benchmarks

Capability profile from matched benchmarks

Our tests

SVG short test

Claude Haiku 4.5

Gemini 3.5 Flash

Pelican on a bicycle

Winning one benchmark is not an overall verdict

Related LLM comparisons