← All Comparisons
Claude Sonnet 4.6 vs GPT-5
A detailed comparison of Claude Sonnet 4.6 (Anthropic) and GPT-5 (OpenAI) across pricing, performance, and features.
Pricing Comparison
| Metric | Claude Sonnet 4.6 | GPT-5 | Difference |
|---|---|---|---|
| Input / 1M tokens | $3.00 | $1.25 | -58% |
| Output / 1M tokens | $15.00 | $10.00 | -33% |
| Context window | 200K | 128K | — |
| Max output | 16K | 16.384K | — |
Benchmark Comparison
| Benchmark | Claude Sonnet 4.6 | GPT-5 |
|---|---|---|
| MMLU-Pro | 86% | 88.5% |
| HumanEval | 94% | 95% |
| GPQA | 70% | 73.5% |
Capabilities
| Capability | Claude Sonnet 4.6 | GPT-5 |
|---|---|---|
| audio | ✗ | ✓ |
| code | ✓ | ✓ |
| reasoning | ✓ | ✓ |
| text | ✓ | ✓ |
| tool-use | ✓ | ✓ |
| vision | ✓ | ✓ |
Claude Sonnet 4.6 Strengths
- ✓Opus 4.5 quality at 1/5th the cost
- ✓Best value for production workloads
- ✓1M context in beta
Claude Sonnet 4.6 Weaknesses
- ✗Long context pricing doubles above 200K
- ✗Slightly below Opus 4.6 on hardest tasks
GPT-5 Strengths
- ✓Strong all-around performance
- ✓Good price for flagship tier
- ✓Multimodal including audio
GPT-5 Weaknesses
- ✗128K context vs 200K+ for newer models
- ✗Codex variants better for pure coding
Quick Verdict
Best value: GPT-5 is the more affordable option at $1.25/$10 per 1M tokens.
Higher benchmarks: GPT-5 scores higher on average across available benchmarks (85.7% avg).
Larger context: Claude Sonnet 4.6 supports 200K tokens.
Choose GPT-5 if cost matters most. Choose Claude Sonnet 4.6 if you need the best possible quality for complex tasks.