Key Takeaways
Claude 3.5 Sonnet wins:
- Larger context window
- Higher intelligence benchmark
- Better at coding
GPT-4o-mini wins:
- Cheaper input tokens
- Cheaper output tokens
- Faster response time
- Better at math
Price Advantage
GPT-4o-mini
Benchmark Advantage
Claude 3.5 Sonnet
Context Window
Claude 3.5 Sonnet
Speed
GPT-4o-mini
Pricing Comparison
Price Comparison
| Metric | Claude 3.5 Sonnet | GPT-4o-mini | Winner |
|---|---|---|---|
| Input (per 1M tokens) | $6.00 | $0.15 | GPT-4o-mini |
| Output (per 1M tokens) | $30.00 | $0.60 | GPT-4o-mini |
| Cache Read (per 1M) | $0.60 | $0.07 | GPT-4o-mini |
| Cache Write (per 1M) | $7.50 | N/A | Claude 3.5 Sonnet |
Using a 3:1 input/output ratio, GPT-4o-mini is 98% cheaper overall.
Claude 3.5 Sonnet Providers
Vercel $3.00 (Cheapest)
Amazon Bedrock $6.00
GPT-4o-mini Providers
OpenAI $0.15 (Cheapest)
Vercel $0.15 (Cheapest)
Azure $0.15 (Cheapest)
Benchmark Comparison
8
Benchmarks Compared
6
Claude 3.5 Sonnet Wins
0
GPT-4o-mini Wins
Benchmark Scores
| Benchmark | Claude 3.5 Sonnet | GPT-4o-mini | Winner |
|---|---|---|---|
Intelligence Index Overall intelligence score | 15.9 | 12.6 | |
Coding Index Code generation & understanding | 30.2 | - | - |
Math Index Mathematical reasoning | - | 14.7 | - |
MMLU Pro Academic knowledge | 77.2 | 64.8 | |
GPQA Graduate-level science | 59.9 | 42.6 | |
LiveCodeBench Competitive programming | 38.1 | 23.4 | |
Aider Real-world code editing | 84.2 | 55.6 | |
AIME Competition math | 15.7 | 11.7 |
Claude 3.5 Sonnet significantly outperforms in coding benchmarks.
Cost vs Quality
X-axis:
Y-axis:
Loading chart...
Claude 3.5 Sonnet
Other models
Context & Performance
Context Window
Claude 3.5 Sonnet
200,000
tokens
Max output: 8,192 tokens
GPT-4o-mini
128,000
tokens
Max output: 16,384 tokens
Claude 3.5 Sonnet has a 36% larger context window.
Speed Performance
| Metric | Claude 3.5 Sonnet | GPT-4o-mini | Winner |
|---|---|---|---|
| Tokens/second | 0.0 tok/s | 53.3 tok/s | |
| Time to First Token | 0.00s | 0.56s |
GPT-4o-mini responds Infinity% faster on average.
Capabilities
Feature Comparison
| Feature | Claude 3.5 Sonnet | GPT-4o-mini |
|---|---|---|
| Vision (Image Input) | ||
| Tool/Function Calls | ||
| Reasoning Mode | ||
| Audio Input | ||
| Audio Output | ||
| PDF Input | ||
| Prompt Caching | ||
| Web Search |
License & Release
| Property | Claude 3.5 Sonnet | GPT-4o-mini |
|---|---|---|
| License | Proprietary | Proprietary |
| Author | Anthropic | OpenAI |
| Released | Oct 2024 | Jul 2024 |
Claude 3.5 Sonnet Modalities
Input
textimagefile
Output
text
GPT-4o-mini Modalities
Input
textimagefile
Output
text