Claude Sonnet 4.5
Head-to-head comparison
Claude Sonnet 4.5 vs. GPT-5.6 Luna
Compare published benchmark results from matching versions and cohorts, API pricing, and technical specifications. Any documented test setup differences remain visible.
- shared result series
- 11
- distinct benchmark metrics
- 4
- 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.
| Attribute | Claude Sonnet 4.5 | GPT-5.6 Luna |
|---|---|---|
| Provider | Anthropic | OpenAI |
| Released | Sep 2025 | Jul 9, 2026 |
| Availability | Active | Active |
| Model type | Proprietary | Proprietary |
| Parameters | Not published | Not published |
| Architecture | Not published | Not published |
| Context window | 200,000 tokens | 1,050,000 tokens |
| Knowledge cutoff | January 2025 | February 16, 2026 |
| Technical sources | Model, Context | Model, Context, 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.
| Price type | Claude Sonnet 4.5 | GPT-5.6 Luna |
|---|---|---|
| API input | $3 | $0.2 ≤272K / $0.4 >272K |
| API output | $15 | $1.2 ≤272K / $1.8 >272K |
| Cache read | $0.3 | $0.02 ≤272K / $0.04 >272K |
| Cache write (5 min.) | $3.75 | $0.25 ≤272K / $0.5 >272K |
| Cache write (1 hr.) | $6 | Not listed |
| Price verified | 09/22/2026 Source | 09/22/2026 Source |
Claude Sonnet 4.5GPT-5.6 Luna
API inputUSD per 1M tokens, base tier
Claude Sonnet 4.5$3
GPT-5.6 LunaLower price$0.2
API outputUSD per 1M tokens, base tier
Claude Sonnet 4.5$15
GPT-5.6 LunaLower price$1.2
Cache readUSD per 1M tokens, base tier
Claude Sonnet 4.5$0.3
GPT-5.6 LunaLower price$0.02
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.
| Model | Provider | Purchase route and tariff | Input per 1M tokens | Output per 1M tokens | Source |
|---|---|---|---|---|---|
| Claude Sonnet 4.5 | Anthropic | Direct from developerStandard API | Lowest listed price: $3 | Lowest listed price: $15 | Source09/22/2026 |
| Amazon Bedrock | Via OpenRouteramazon-bedrock | Lowest listed price: $3 | Lowest listed price: $15 | Source10/26/2026 | |
| Amazon Bedrock | Via OpenRouteramazon-bedrock/eu-west-1 | $3.3 | $16.5 | Source10/26/2026 | |
| Anthropic | Via OpenRouteranthropic | Lowest listed price: $3 | Lowest listed price: $15 | Source10/26/2026 | |
| Azure | Via OpenRouterazure/global | Lowest listed price: $3 | Lowest listed price: $15 | Source10/26/2026 | |
| Claude Platform on AWS | Via OpenRouterclaude-on-aws | Lowest listed price: $3 | Lowest listed price: $15 | Source10/26/2026 | |
| Via OpenRoutergoogle-vertex/global | Lowest listed price: $3 | Lowest listed price: $15 | Source10/26/2026 | ||
| Via OpenRoutergoogle-vertex/us-east5 | $3.3 | $16.5 | Source10/26/2026 | ||
| GPT-5.6 Luna | OpenAI | Direct from developerUp to 272,000 context tokens | $0.2 | $1.2 | Source09/22/2026 |
| OpenAI | Direct from developerAbove 272,000 context tokens | $0.4 | $1.8 | Source09/22/2026 | |
| Amazon Bedrock | Via OpenRouteramazon-bedrock/us-east-1 | $0.22 | $1.32 | Source10/26/2026 | |
| Azure | Via OpenRouterazure | $0.2 | $1.2 | Source10/26/2026 | |
| Azure | Via OpenRouterazure/eu | $0.22 | $1.32 | Source10/26/2026 | |
| Azure | Via OpenRouterazure/us | $0.22 | $1.32 | Source10/26/2026 | |
| OpenAI | Via OpenRouteropenai | $0.2 | $1.2 | Source10/26/2026 | |
| OpenAI | Via OpenRouteropenai/fast | $0.4 | $2.4 | Source10/26/2026 | |
| OpenAI | Via OpenRouteropenai/flex | Lowest listed price: $0.1 | Lowest listed price: $0.6 | 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.
GPT-5.6 Luna leads in 4 of 4 shared areas.
| Area | Claude Sonnet 4.5 | GPT-5.6 Luna |
|---|---|---|
| Finance | 7.7 | 52.8 |
| Legal | 7.9 | 29.8 |
| Health | 16.9 | 34.5 |
| Education | 4.6 | 37.4 |
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 4.5GPT-5.6 Luna
CorpFin v2Overall. Higher is better. Test setup not documented as identical
Claude Sonnet 4.560.8 %
GPT-5.6 LunaHigher measured value64.219 %
MedCodeOverall. Higher is better. Test setup not documented as identical
Claude Sonnet 4.540.569 %
GPT-5.6 LunaHigher measured value42.391 %
MedScribeOverall. Higher is better. Test setup not documented as identical
Claude Sonnet 4.5Higher measured value84.515 %
GPT-5.6 Luna84.391 %
SAGEOverall. Higher is better. Test setup not documented as identical
Claude Sonnet 4.532.88 %
GPT-5.6 LunaHigher measured value44.22 %
CorpFin v2Exact Pages. Higher is better. Test setup not documented as identical
Claude Sonnet 4.560.373 %
GPT-5.6 LunaHigher measured value63.52 %
SAGEAutomata. Higher is better. Test setup not documented as identical
Claude Sonnet 4.520.238 %
GPT-5.6 LunaHigher measured value31.35 %
CorpFin v2Max Fitting Context. Higher is better. Test setup not documented as identical
Claude Sonnet 4.561.538 %
GPT-5.6 LunaHigher measured value64.103 %
SAGECalculus. Higher is better. Test setup not documented as identical
Claude Sonnet 4.537.654 %
GPT-5.6 LunaHigher measured value64.506 %
CorpFin v2Shared Max Context. Higher is better. Test setup not documented as identical
Claude Sonnet 4.560.49 %
GPT-5.6 LunaHigher measured value65.035 %
SAGELinear Algebra. Higher is better. Test setup not documented as identical
Claude Sonnet 4.551.417 %
GPT-5.6 LunaHigher measured value63.216 %
SAGEPartial Differential Equations. Higher is better. Test setup not documented as identical
Claude Sonnet 4.526.984 %
GPT-5.6 LunaHigher measured value38.095 %
Key to the marks:better valuebetter, but not conclusivetie
| Benchmark and task | Claude Sonnet 4.5 | GPT-5.6 Luna | Source |
|---|---|---|---|
CorpFin v2OverallTest detailsTest setup not documented as identicalNo direct winnerVersion: 2Metric: accuracyScoring: Higher is betterClaude Sonnet 4.5: Snapshot: claude-sonnet-4-5-20250929, Temperature: 1, Output limit: 64,000 tokens GPT-5.6 Luna: Reasoning: max, Output limit: 128,000 tokens | 60.8 % | Higher measured value64.219 % | Vals AISource detailsData as of: 08/12/2026 |
MedCodeOverallTest detailsTest 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 GPT-5.6 Luna: Reasoning: max, Output limit: 30,000 tokens | 40.569 % | Higher measured value42.391 % | Vals AISource detailsData as of: 10/13/2026 |
MedScribeOverallTest detailsTest 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 GPT-5.6 Luna: Reasoning: max, Output limit: 30,000 tokens | Higher measured value84.515 % | 84.391 % | Vals AISource detailsData as of: 10/13/2026 |
SAGEOverallTest detailsTest 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 GPT-5.6 Luna: Reasoning: max, Output limit: 30,000 tokens | 32.88 % | Higher measured value44.22 % | Vals AISource detailsData as of: 10/08/2026 |
CorpFin v2Exact PagesTest detailsTest setup not documented as identicalNo direct winnerVersion: 2Metric: accuracyScoring: Higher is betterClaude Sonnet 4.5: Snapshot: claude-sonnet-4-5-20250929, Temperature: 1, Output limit: 64,000 tokens GPT-5.6 Luna: Reasoning: max, Output limit: 128,000 tokens | 60.373 % | Higher measured value63.52 % | Vals AISource detailsData as of: 08/12/2026 |
SAGEAutomataTest detailsTest 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 GPT-5.6 Luna: Reasoning: max, Output limit: 30,000 tokens | 20.238 % | Higher measured value31.35 % | Vals AISource detailsData as of: 10/08/2026 |
CorpFin v2Max Fitting ContextTest detailsTest setup not documented as identicalNo direct winnerVersion: 2Metric: accuracyScoring: Higher is betterClaude Sonnet 4.5: Snapshot: claude-sonnet-4-5-20250929, Temperature: 1, Output limit: 64,000 tokens GPT-5.6 Luna: Reasoning: max, Output limit: 128,000 tokens | 61.538 % | Higher measured value64.103 % | Vals AISource detailsData as of: 08/12/2026 |
SAGECalculusTest detailsTest 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 GPT-5.6 Luna: Reasoning: max, Output limit: 30,000 tokens | 37.654 % | Higher measured value64.506 % | Vals AISource detailsData as of: 10/08/2026 |
CorpFin v2Shared Max ContextTest detailsTest setup not documented as identicalNo direct winnerVersion: 2Metric: accuracyScoring: Higher is betterClaude Sonnet 4.5: Snapshot: claude-sonnet-4-5-20250929, Temperature: 1, Output limit: 64,000 tokens GPT-5.6 Luna: Reasoning: max, Output limit: 128,000 tokens | 60.49 % | Higher measured value65.035 % | Vals AISource detailsData as of: 08/12/2026 |
SAGELinear AlgebraTest detailsTest 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 GPT-5.6 Luna: Reasoning: max, Output limit: 30,000 tokens | 51.417 % | Higher measured value63.216 % | Vals AISource detailsData as of: 10/08/2026 |
SAGEPartial Differential EquationsTest detailsTest 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 GPT-5.6 Luna: Reasoning: max, Output limit: 30,000 tokens | 26.984 % | Higher measured value38.095 % | Vals AISource detailsData 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
GPT-5.6 Luna
Unavailable in this round
Earlier tests
Pelican on a bicycle
A community classic for free-form SVG drawing.
Claude Sonnet 4.5
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.
GPT-5.6 Luna
Reasoning (requested): high
Current attempt
- Run date
- Sep 7, 2026
- API provider
- openrouter
- Requested API model
- openai/gpt-5.6-luna
- API model reported in response
- openai/gpt-5.6-luna
- Reasoning setting
- high
- Pinned endpoint
- OpenAI | openai/gpt-5.6-luna-20260709
- 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
- 49.9 s
Visually reviewed. This individual test does not establish overall model quality.
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 GPT-5.6 Luna with other leading models using the same data and benchmark logic.