All Comparisons
Claude Opus 4 vs GPT-4o
Claude Opus 4
Anthropic 🇺🇸
75.1
#52—
high$15.00/M in · $75.00/M out
200K context
GPT-4o
OpenAI 🇺🇸
58.3
#136—
high$2.50/M in · $10.00/M out
128K context
Most Affordable
GPT-4o
$2.50/M input
Largest Context
Claude Opus 4
200K tokens
Best Benchmark Score
Claude Opus 4
75.1/100
Model Specifications
| Spec | Claude Opus 4 | GPT-4o |
|---|---|---|
| Provider | Anthropic | OpenAI |
| Release Date | May 2025 | May 2024 |
| Knowledge Cutoff | Mar 2025 | Oct 2023 |
| Parameters | unknown | unknown |
| Context Window | 200K | 128K |
| 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 Opus 4 | GPT-4o |
|---|---|---|
| Input | $15.00 | $2.50 |
| Output | $75.00 | $10.00 |
API Provider Pricing
Capabilities
| Feature | Claude Opus 4 | GPT-4o |
|---|---|---|
| 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 Opus 4 | GPT-4o |
|---|---|---|
| Chatbot Arena Elo | 1365 | 1285 |
| IFEval | 91.5 | 83.6 |
| MMLU-Pro | 83.5 | 74.5 |
coding
| Benchmark | Claude Opus 4 | GPT-4o |
|---|---|---|
| HumanEval | 95.1 | 90.2 |
| SWE-bench Verified | 55.8 | 33.2 |
reasoning
| Benchmark | Claude Opus 4 | GPT-4o |
|---|---|---|
| GPQA Diamond | 74.8 | 53.6 |
| BigBench-Hard | 93.2 | 87.3 |
| ARC-Challenge | — | 96.4 |
multimodal
| Benchmark | Claude Opus 4 | GPT-4o |
|---|---|---|
| MMMU | 74.2 | 69.1 |
language
| Benchmark | Claude Opus 4 | GPT-4o |
|---|---|---|
| HellaSwag | — | 96.4 |
| WinoGrande | — | 85.7 |
safety
| Benchmark | Claude Opus 4 | GPT-4o |
|---|---|---|
| TruthfulQA | — | 73.5 |
Category Winners
coding
58.1
math
75.5
reasoning
79.7
general
96.0
language
79.9
multimodal
67.8
safety
94.3