All Comparisons
GPT-4o vs Claude Sonnet 4
GPT-4o
OpenAI 🇺🇸
58.1
#145—
high$2.50/M in · $10.00/M out
128K context
Claude Sonnet 4
Anthropic 🇺🇸
68.3
#93—
high$3.00/M in · $15.00/M out
1M context
Most Affordable
GPT-4o
$2.50/M input
Largest Context
Claude Sonnet 4
1M tokens
Best Benchmark Score
Claude Sonnet 4
68.3/100
Model Specifications
| Spec | GPT-4o | Claude Sonnet 4 |
|---|---|---|
| Provider | OpenAI | Anthropic |
| Release Date | May 2024 | May 2025 |
| Knowledge Cutoff | 2023-10-31 | 2025-01-31 |
| Parameters | unknown | unknown |
| Context Window | 128K | 1M |
| Max Output | 16.4K | 64K |
| Open Source | No | No |
| License | proprietary | proprietary |
| Tokenizer | GPT | Claude |
| Modality | text+image+file->text | text+image+file->text |
| Reasoning Model | No | No |
| Moderated | Yes | Yes |
Pricing Comparison
| Price (per 1M tokens) | GPT-4o | Claude Sonnet 4 |
|---|---|---|
| Input | $2.50 | $3.00 |
| Output | $10.00 | $15.00 |
| Cache Read | $1.25 | $0.30 |
| Cache Write | — | $3.75 |
API Provider Pricing
Capabilities
| Feature | GPT-4o | Claude Sonnet 4 |
|---|---|---|
| Text Input | ||
| Image Input (Vision) | ||
| Audio Input | ||
| Video Input | ||
| File Input | ||
| Image Output | ||
| Audio Output | ||
| Tool Use | ||
| Structured Output (JSON) | ||
| Streaming | ||
| Reasoning Tokens | ||
| Web Search | ||
| Temperature Control | ||
| Top-P Sampling | ||
| Stop Sequences | ||
| Seed (Reproducibility) | ||
| Log Probabilities |
Category Comparison
Benchmark-by-Benchmark
general
| Benchmark | GPT-4o | Claude Sonnet 4 |
|---|---|---|
| MMLU-Pro | 74.5 | 80.2 |
| Chatbot Arena Elo | 1285 | 1310 |
| IFEval | 83.6 | 90.1 |
coding
| Benchmark | GPT-4o | Claude Sonnet 4 |
|---|---|---|
| HumanEval | 90.2 | 93.8 |
| SWE-bench Verified | 33.2 | 53.2 |
reasoning
| Benchmark | GPT-4o | Claude Sonnet 4 |
|---|---|---|
| BigBench-Hard | 87.3 | 90.8 |
| ARC-Challenge | 96.4 | — |
| GPQA Diamond | 53.6 | 70.5 |
language
| Benchmark | GPT-4o | Claude Sonnet 4 |
|---|---|---|
| WinoGrande | 85.7 | — |
| HellaSwag | 96.4 | — |
multimodal
| Benchmark | GPT-4o | Claude Sonnet 4 |
|---|---|---|
| MMMU | 69.1 | 72.5 |
safety
| Benchmark | GPT-4o | Claude Sonnet 4 |
|---|---|---|
| TruthfulQA | 73.5 | — |
Category Winners
coding
53.9
math
66.8
reasoning
70.5
general
90.0
language
79.9
multimodal
62.3
safety
94.3