Claude Sonnet 4.5
Not tested yet
Head-to-head comparison
Claude Sonnet 4.5 vs. Gemini 3.1 Pro Preview
Compare published benchmark results from matching versions and cohorts, API pricing, and technical specifications. Any documented test setup differences remain visible.
- shared result series
- 9
- distinct benchmarks
- 6
- latest retrieval
- 2026-08-26
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 | Gemini 3.1 Pro Preview |
|---|---|---|
| Provider | Anthropic | |
| Released | Sep 2025 | Feb 19, 2026 |
| Availability | Active | Preview |
| 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 | January 2025 | Not published |
| Technical sources | Model, Context | 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.
| Price type | Claude Sonnet 4.5 | Gemini 3.1 Pro Preview |
|---|---|---|
| API input | $3 | $2 ≤200K / $4 >200K |
| API output | $15 | $12 ≤200K / $18 >200K |
| Cache read | $0.3 | $0.2 ≤200K / $0.4 >200K |
| Cache write (5 min.) | $3.75 | Not listed |
| Cache write (1 hr.) | $6 | Not listed |
| Price verified | 07/30/2026 Source | 07/30/2026 Source |
Claude Sonnet 4.5Gemini 3.1 Pro Preview
API inputUSD per 1M tokens, base tier
Claude Sonnet 4.5$3
Gemini 3.1 Pro PreviewLower price$2
API outputUSD per 1M tokens, base tier
Claude Sonnet 4.5$15
Gemini 3.1 Pro PreviewLower price$12
Cache readUSD per 1M tokens, base tier
Claude Sonnet 4.5$0.3
Gemini 3.1 Pro PreviewLower price$0.2
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 | Source07/30/2026 |
| Amazon Bedrock | Via OpenRouteramazon-bedrock | Lowest listed price: $3 | Lowest listed price: $15 | Source09/12/2026 | |
| Amazon Bedrock | Via OpenRouteramazon-bedrock/eu-west-1 | $3.3 | $16.5 | Source09/12/2026 | |
| Anthropic | Via OpenRouteranthropic | Lowest listed price: $3 | Lowest listed price: $15 | Source09/12/2026 | |
| Azure | Via OpenRouterazure/global | Lowest listed price: $3 | Lowest listed price: $15 | Source09/12/2026 | |
| Claude Platform on AWS | Via OpenRouterclaude-on-aws | Lowest listed price: $3 | Lowest listed price: $15 | Source09/12/2026 | |
| Via OpenRoutergoogle-vertex/global | Lowest listed price: $3 | Lowest listed price: $15 | Source09/12/2026 | ||
| Via OpenRoutergoogle-vertex/us-east5 | $3.3 | $16.5 | Source09/12/2026 | ||
| Gemini 3.1 Pro Preview | Direct from developerUp to 200,000 context tokens | $2 | $12 | Source07/30/2026 | |
| Direct from developerAbove 200,000 context tokens | $4 | $18 | Source07/30/2026 | ||
| Via OpenRoutergoogle-vertex/global | $2 | $12 | Source09/12/2026 | ||
| Via OpenRoutergoogle-vertex/global/flex | Lowest listed price: $1 | Lowest listed price: $6 | Source09/12/2026 | ||
| Via OpenRoutergoogle-vertex/global/priority | $3.6 | $21.6 | Source09/12/2026 | ||
| Google AI Studio | Via OpenRoutergoogle-ai-studio | $2 | $12 | Source09/12/2026 | |
| Google AI Studio | Via OpenRoutergoogle-ai-studio/flex | Lowest listed price: $1 | Lowest listed price: $6 | Source09/12/2026 | |
| Google AI Studio | Via OpenRoutergoogle-ai-studio/priority | $3.6 | $21.6 | Source09/12/2026 |
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.
Claude Sonnet 4.5
Gemini 3.1 Pro Preview
Reasoning: 43.5 / 100 (1 benchmark family)
Finance: 100 / 95.6 (1 benchmark family)
Legal: 92.8 / 100 (1 benchmark family)
Multimodal: 19.3 / 100 (1 benchmark family)
Education: 86.2 / 100 (1 benchmark family)
5 matched rows from 5 benchmark families were considered. The radar shows 5 of 5 comparable categories.
Claude Sonnet 4.5Gemini 3.1 Pro Preview
MultiChallengeOverall. Higher is better. Test setup not documented as identical
Claude Sonnet 4.555.32% ± 1.47
Gemini 3.1 Pro PreviewHigher measured value71.37% ± 1.74
MultiNRCOverall. Higher is better. No documented setup difference
Claude Sonnet 4.528.15% ± 2.71
Gemini 3.1 Pro PreviewWinner64.74% ± 2.88
PRBench FinanceOverall. Higher is better. No documented setup difference
Claude Sonnet 4.5Winner43.79% ± 0.4
Gemini 3.1 Pro Preview41.87% ± 1.22
PRBench LegalOverall. Higher is better. No documented setup difference
Claude Sonnet 4.540.84% ± 0.4
Gemini 3.1 Pro PreviewWinner44.02% ± 1.12
TutorBenchOverall. Higher is better. No documented setup difference
Claude Sonnet 4.545.7% ± 1.01
Gemini 3.1 Pro PreviewWinner52.99% ± 1.06
VisualToolBenchOverall. Higher is better. No documented setup difference
Claude Sonnet 4.55.6% ± 0.12
Gemini 3.1 Pro PreviewWinner28.97% ± 0.91
MultiNRCOverall. Higher is better. Test setup not documented as identical
Claude Sonnet 4.535.83% ± 2.89
Gemini 3.1 Pro PreviewHigher measured value64.74% ± 2.88
TutorBenchOverall. Higher is better. Test setup not documented as identical
Claude Sonnet 4.549% ± 1.01
Gemini 3.1 Pro PreviewHigher measured value52.99% ± 1.06
VisualToolBenchOverall. Higher is better. Test setup not documented as identical
Claude Sonnet 4.56.2% ± 0.14
Gemini 3.1 Pro PreviewHigher measured value28.97% ± 0.91
Key to the marks:better valuebetter, but not conclusivetie
| Benchmark and task | Claude Sonnet 4.5 | Gemini 3.1 Pro Preview | Source |
|---|---|---|---|
MultiChallengeOverallTest detailsTest setup not documented as identicalNo direct winnerVersion: four multi-turn challenge typesMetric: rubric pass rateScoring: Higher is betterClaude Sonnet 4.5: Reasoning: thinking, Attempts: pass@1 Gemini 3.1 Pro Preview: Attempts: pass@1Multi-turn conversations with binary task-specific rubrics. | 55.32% ± 1.47 95% confidence interval: ±1.47 | Higher measured value71.37% ± 1.74 95% confidence interval: ±1.74 | Scale AISource detailsData as of: 08/26/2026 |
MultiNRCOverallTest detailsNo documented difference in the test setupVersion: French, Spanish, and Chinese releaseMetric: accuracyScoring: Higher is betterSettings: Attempts: pass@1Native, non-translated reasoning tasks with automatic evaluation. | 28.15% ± 2.71 95% confidence interval: ±2.71 | Winner64.74% ± 2.88 95% confidence interval: ±2.88 | Scale AISource detailsData as of: 08/26/2026 |
PRBench FinanceOverallTest detailsNo documented difference in the test setupVersion: full finance setMetric: weighted rubric scoreScoring: Higher is betterSettings: Attempts: pass@1600 finance tasks with task-specific rubrics and o4-mini as judge. | Winner43.79% ± 0.4 95% confidence interval: ±0.4 | 41.87% ± 1.22 95% confidence interval: ±1.22 | Scale AISource detailsData as of: 08/26/2026 |
PRBench LegalOverallTest detailsNo documented difference in the test setupVersion: full legal setMetric: weighted rubric scoreScoring: Higher is betterSettings: Attempts: pass@1500 legal tasks with task-specific rubrics and o4-mini as judge. | 40.84% ± 0.4 95% confidence interval: ±0.4 | Winner44.02% ± 1.12 95% confidence interval: ±1.12 | Scale AISource detailsData as of: 08/26/2026 |
TutorBenchOverallTest detailsNo documented difference in the test setupVersion: 1,490-task releaseMetric: weighted rubric scoreScoring: Higher is betterSettings: Attempts: pass@11,490 tasks with weighted rubrics and Claude 4 Sonnet as judge. | 45.7% ± 1.01 95% confidence interval: ±1.01 | Winner52.99% ± 1.06 95% confidence interval: ±1.06 | Scale AISource detailsData as of: 08/26/2026 |
VisualToolBenchOverallTest detailsNo documented difference in the test setupVersion: 1,204-task releaseMetric: average pass rateScoring: Higher is betterSettings: Attempts: pass@11,204 tasks, six tools, and at most 20 tool calls per task. | 5.6% ± 0.12 95% confidence interval: ±0.12 | Winner28.97% ± 0.91 95% confidence interval: ±0.91 | Scale AISource detailsData as of: 08/26/2026 |
MultiNRCOverallTest detailsTest setup not documented as identicalNo direct winnerVersion: French, Spanish, and Chinese releaseMetric: accuracyScoring: Higher is betterClaude Sonnet 4.5: Reasoning: thinking, Attempts: pass@1 Gemini 3.1 Pro Preview: Attempts: pass@1Native, non-translated reasoning tasks with automatic evaluation. | 35.83% ± 2.89 95% confidence interval: ±2.89 | Higher measured value64.74% ± 2.88 95% confidence interval: ±2.88 | Scale AISource detailsData as of: 08/26/2026 |
TutorBenchOverallTest detailsTest setup not documented as identicalNo direct winnerVersion: 1,490-task releaseMetric: weighted rubric scoreScoring: Higher is betterClaude Sonnet 4.5: Reasoning: thinking, Attempts: pass@1 Gemini 3.1 Pro Preview: Attempts: pass@11,490 tasks with weighted rubrics and Claude 4 Sonnet as judge. | 49% ± 1.01 95% confidence interval: ±1.01 | Higher measured value52.99% ± 1.06 95% confidence interval: ±1.06 | Scale AISource detailsData as of: 08/26/2026 |
VisualToolBenchOverallTest detailsTest setup not documented as identicalNo direct winnerVersion: 1,204-task releaseMetric: average pass rateScoring: Higher is betterClaude Sonnet 4.5: Reasoning: thinking, Attempts: pass@1 Gemini 3.1 Pro Preview: Attempts: pass@11,204 tasks, six tools, and at most 20 tool calls per task. | 6.2% ± 0.14 95% confidence interval: ±0.14 | Higher measured value28.97% ± 0.91 95% confidence interval: ±0.91 | Scale AISource detailsData as of: 08/26/2026 |
Key to the marks:better valuebetter, but not conclusivetie | |||
Our model tests
Community tests you can inspect
Compare how the models respond to the same prompt. Each test shows the first attempt, with no subsequent fixes to the generated code. These results do not contribute to an overall score.
Pelican on a bicycle
A community classic for free-form SVG drawing.
Gemini 3.1 Pro Preview
API access was unavailable for this run. The model was not evaluated.
First attempt
- Run date
- 7 Sept 2026
- API provider
- openrouter
- Requested API model
- google/gemini-3.1-pro-preview
- Pinned endpoint
- Google AI Studio | google/gemini-3.1-pro-preview-20260219
- Reasoning setting
- high
- Temperature
- Provider default
- Token limit including reasoning
- 8,192 tokens
- Test protocol
- community-visual-tests-v1
- Technical checks
- Not run
Not yet visually reviewed. A successful recording does not confirm correct physics or full compliance with the prompt.
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 3.1 Pro Preview with other leading models using the same data and benchmark logic.