Model Comparison
Claude 3.5 Sonnet (June '24)
vs. GPT-4o mini
Comparing 2 AI models · 9 benchmarks · Anthropic, OpenAI
Recommended Pick
Op GPT-4o mini 8 metric wins Strongest on: Value, Input price, Output price
Best Value
GPT-4o mini
100.0 value score
25.6 reasoning / $0.26/1M
Lowest Price
GPT-4o mini
$0.15/1M input price
Best Reasoning
Claude 3.5 Sonnet (June '24)
30.6 reasoning score
Blends available reasoning benchmarks
Best for Coding
Claude 3.5 Sonnet (June '24)
26.0 coding index
Composite Indices
Higher is better; speed and price are normalized
Standard Benchmarks
Only benchmarks with data are shown
Differences That Matter
Best value
GPT-4o mini has the strongest quality-to-price mix at 100.0 out of 100 value points.
Price gap
GPT-4o mini is 25x cheaper on input tokens than Claude 3.5 Sonnet (June '24).
Reasoning gap
Claude 3.5 Sonnet (June '24) leads GPT-4o mini by 5.0 points on reasoning.
Top-pick rationale
GPT-4o mini wins 8 measurable categories, including Value, Input price, Output price, Blended price.
Response Face-Off
Run one prompt through the selected models and compare response quality with live speed and cost context.
Claude 3.5 Sonnet (June '24)
Anthropic
TTFT
—
Time
—
tok/s
—
Tokens
—
Cost
—
GPT-4o mini
OpenAI
TTFT
—
Time
—
tok/s
—
Tokens
—
Cost
—
Which answer was more useful?
Full Comparison
| Metric | An Claude 3.5 Sonnet (June '24) | Top Pick Op GPT-4o mini |
|---|---|---|
| Pricing per 1M tokens | ||
| Input Cost | $3.75/1M | $0.15/1M |
| Output Cost | $15.00/1M | $0.60/1M |
| Blended (3:1) | $6.56/1M | $0.26/1M |
| Specifications | ||
| Organization | Anthropic | OpenAI |
| Release Date | Jun 21, 2024 | Jul 18, 2024 |
| Performance & Speed | ||
| Throughput | — | 71.7 tok/s |
| TTFT | — | 587ms |
| Latency | — | 587ms |
| Composite Indices | ||
| Value Score | 4.8 | 100.0 |
| Reasoning Score | 30.6 | 25.6 |
| Intelligence | 14.2 | 12.6 |
| Coding | 26.0 | — |
| Math | — | 14.7 |
| Standard Benchmarks | ||
| GPQA | 56.0% | 42.6% |
| MMLU Pro | 75.1% | 64.8% |
| HLE | 3.7% | 4.0% |
| LiveCodeBench | — | 23.4% |
| MATH 500 | 69.5% | 78.9% |
| AIME 2025 | — | 14.7% |
| AIME (Original) | 9.7% | 11.7% |
| SciCode | 31.6% | 22.9% |
| IFBench | — | 31.0% |
Key Takeaways
GPT-4o mini offers the best value at $0.15/1M, making it ideal for high-volume applications and cost-conscious projects.
Claude 3.5 Sonnet (June '24) has the strongest reasoning profile with a 30.6 reasoning score, combining the available reasoning-heavy benchmarks.
Claude 3.5 Sonnet (June '24) reaches a 26.0 coding index, making it the top choice for software development and code generation tasks.
All models support context windows of ∞+ tokens, suitable for processing lengthy documents and maintaining extended conversations.
When to Choose Each Model
Claude 3.5 Sonnet (June '24)
- Complex reasoning tasks
- Research & analysis
- Code generation
- Software development
GPT-4o mini
- Cost-sensitive applications
- High-volume processing
