All Comparisons
Claude Sonnet 4 vs GPT-4.1
Claude Sonnet 4
Anthropic 🇺🇸
68.5
#83—
high$3.00/M in · $15.00/M out
200K context
GPT-4.1
OpenAI 🇺🇸
32.8
#238—
high$2.00/M in · $8.00/M out
1.0M context
Most Affordable
GPT-4.1
$2.00/M input
Largest Context
GPT-4.1
1.0M tokens
Best Benchmark Score
Claude Sonnet 4
68.5/100
Model Specifications
| Spec | Claude Sonnet 4 | GPT-4.1 |
|---|---|---|
| Provider | Anthropic | OpenAI |
| Release Date | May 2025 | Apr 2025 |
| Knowledge Cutoff | Mar 2025 | 2024-06-01 |
| Parameters | unknown | Undisclosed |
| Context Window | 200K | 1.0M |
| Max Output | — | — |
| Open Source | No | No |
| License | proprietary | proprietary |
| Tokenizer | — | — |
| Modality | — | — |
| Reasoning Model | No | No |
| Moderated | No | No |
Pricing Comparison
| Price (per 1M tokens) | Claude Sonnet 4 | GPT-4.1 |
|---|---|---|
| Input | $3.00 | $2.00 |
| Output | $15.00 | $8.00 |
API Provider Pricing
Capabilities
| Feature | Claude Sonnet 4 | GPT-4.1 |
|---|---|---|
| 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 | Claude Sonnet 4 | GPT-4.1 |
|---|---|---|
| IFEval | 90.1 | — |
| MMLU-Pro | 80.2 | — |
| Chatbot Arena Elo | 1310 | — |
| MMMLU | — | 87.3 |
coding
| Benchmark | Claude Sonnet 4 | GPT-4.1 |
|---|---|---|
| HumanEval | 93.8 | — |
| SWE-bench Verified | 53.2 | 54.6 |
reasoning
| Benchmark | Claude Sonnet 4 | GPT-4.1 |
|---|---|---|
| BigBench-Hard | 90.8 | — |
| GPQA Diamond | 70.5 | 66.3 |
| Humanity's Last Exam | — | 5.4 |
multimodal
| Benchmark | Claude Sonnet 4 | GPT-4.1 |
|---|---|---|
| MMMU | 72.5 | 74.8 |
| CharXiv Reasoning | — | 56.7 |
agent
| Benchmark | Claude Sonnet 4 | GPT-4.1 |
|---|---|---|
| TAU-Bench Retail | — | 68 |
Category Winners
coding
54.0
math
66.8
reasoning
70.9
general
90.0
multimodal
63.3
agent
50.7