Key Takeaways
Claude Sonnet 4 wins:
- No clear advantages in compared metrics
Gemini 2.5 Pro wins:
- Cheaper input tokens
- Cheaper output tokens
- Larger context window
- Faster response time
- Higher intelligence benchmark
- Better at coding
- Better at math
Price Advantage
Gemini 2.5 Pro
Benchmark Advantage
Gemini 2.5 Pro
Context Window
Gemini 2.5 Pro
Speed
Gemini 2.5 Pro
Pricing Comparison
Price Comparison
| Metric | Claude Sonnet 4 | Gemini 2.5 Pro | Winner |
|---|---|---|---|
| Input (per 1M tokens) | $3.00 | $1.25 | Gemini 2.5 Pro |
| Output (per 1M tokens) | $15.00 | $10.00 | Gemini 2.5 Pro |
| Cache Read (per 1M) | $0.30 | $0.13 | Gemini 2.5 Pro |
| Cache Write (per 1M) | $3.75 | $0.38 | Gemini 2.5 Pro |
Using a 3:1 input/output ratio, Gemini 2.5 Pro is 43% cheaper overall.
Claude Sonnet 4 Providers
Amazon Bedrock $3.00 (Cheapest)
Google $3.00 (Cheapest)
Anthropic $3.00 (Cheapest)
Gemini 2.5 Pro Providers
Google AI Studio $1.00 (Cheapest)
Google $1.25
Vercel $2.50
Benchmark Comparison
8
Benchmarks Compared
0
Claude Sonnet 4 Wins
7
Gemini 2.5 Pro Wins
Benchmark Scores
| Benchmark | Claude Sonnet 4 | Gemini 2.5 Pro | Winner |
|---|---|---|---|
Intelligence Index Overall intelligence score | 33.0 | 34.6 | |
Coding Index Code generation & understanding | 30.6 | 31.9 | |
Math Index Mathematical reasoning | 38.0 | 87.7 | |
MMLU Pro Academic knowledge | 83.7 | 86.2 | |
GPQA Graduate-level science | 68.3 | 84.4 | |
LiveCodeBench Competitive programming | 44.9 | 80.1 | |
Aider Real-world code editing | 61.3 | - | - |
AIME Competition math | 40.7 | 88.7 |
Gemini 2.5 Pro shows stronger mathematical reasoning abilities.
Cost vs Quality
X-axis:
Y-axis:
Loading chart...
Claude Sonnet 4
Other models
Context & Performance
Context Window
Claude Sonnet 4
1,000,000
tokens
Max output: 64,000 tokens
Gemini 2.5 Pro
1,048,576
tokens
Max output: 65,536 tokens
Gemini 2.5 Pro has a 5% larger context window.
Speed Performance
| Metric | Claude Sonnet 4 | Gemini 2.5 Pro | Winner |
|---|---|---|---|
| Tokens/second | 69.8 tok/s | 151.8 tok/s | |
| Time to First Token | 1.17s | 35.93s |
Gemini 2.5 Pro responds 118% faster on average.
Capabilities
Feature Comparison
| Feature | Claude Sonnet 4 | Gemini 2.5 Pro |
|---|---|---|
| Vision (Image Input) | ||
| Tool/Function Calls | ||
| Reasoning Mode | ||
| Audio Input | ||
| Audio Output | ||
| PDF Input | ||
| Prompt Caching | ||
| Web Search |
License & Release
| Property | Claude Sonnet 4 | Gemini 2.5 Pro |
|---|---|---|
| License | Proprietary | Proprietary |
| Author | Anthropic | |
| Released | May 2025 | Jun 2025 |
Claude Sonnet 4 Modalities
Input
imagetextfile
Output
text
Gemini 2.5 Pro Modalities
Input
textimagefileaudiovideo
Output
text