LLM Comparison
GPT-5.4 vs Claude Sonnet 4.6
Side-by-side specs, pricing & capabilities · Updated May 2026
Price vs Intelligence
Add to comparison
2/6 modelsSame tier:
| Organization | ||
| OpenTools Score | 74 8.4 | 52 5.7 |
| Family | GPT | Claude |
| Status | Current | Current |
| Release Date | Mar 2026 | Feb 2026 |
| Context Window | 1.1M tokens | 1.0M tokens |
| Input Price | $2.50/M tokens | $3.00/M tokens |
| Output Price | $15.00/M tokens | $15.00/M tokens |
| Pricing Notes | Cache read: $0.2500/M tokens | Cache read: $0.3000/M tokens |
| Capabilities | textvisioncode | textvisioncodetool-use |
| Max Output | 128K tokens | 128K tokens |
| API Identifier | openai/gpt-5.4 | anthropic/claude-sonnet-4.6 |
| Benchmarks | ||
| GPQA Diamond | 93openai | 89.9anthropic |
| SWE-bench Pro | 57.7openai | — |
| OSWorld-Verified | 75openai | — |
| Terminal-Bench 2.0 | 75.1openai | 51anthropic |
| ARC-AGI-2 | 73.3openai | — |
| BrowseComp | 82.7openai | — |
| MMMU-Pro | 81.2openai | — |
| MATH-500 | 94.6openai | — |
| MMLU | — | 86.7anthropic |
| SWE-bench Verified | — | 72.5anthropic |
| MATH 500 | — | 54.2anthropic |
| LiveCodeBench | — | 41.5anthropic |
| Berkeley Function Calling | — | 88.3anthropic |
| HLE | — | 30openrouter |
| GPQA-AA Elo | — | 1674artificial-analysis |
| View GPT-5.4 | View Claude Sonnet 4.6 | |
Cost Calculator
Enter your expected monthly token usage to compare costs.
| Model | Input | Output | Total / mo | vs Best |
|---|---|---|---|---|
| GPT-5.4Cheapest | $2.50 | $7.50 | $10.00 | — |
| Claude Sonnet 4.6 | $3.00 | $7.50 | $10.50 | +5% |
OpenAI
GPT-5.4
GPT-5.4 is a multimodal llm from OpenAI. Supports up to 1,050,000 token context window. Available from $2.50/M input tokens.
Anthropic
Claude Sonnet 4.6
Claude Sonnet 4.6 is a multimodal llm from Anthropic. Supports up to 1,000,000 token context window. Achieves 88.0% on MMLU. Available from $3.00/M input tokens.
More Comparisons
Looking for more AI models?
Browse All LLMs