Compare AI models
Claude Sonnet 4.6vsgpt-5.4-mini
Which should you pick?
- gpt-5.4-mini · overall 63.1 vs 57.2
- gpt-5.4-mini cheaper output · $6.73 vs $19.50 /1M
Specifications
| Claude Sonnet 4.6 | gpt-5.4-mini | |
|---|---|---|
| Tier | A | A |
| Context window | 1.0M tokens | — |
| Input price (per 1M tokens) | $3.90 | $1.13 |
| Output price (per 1M tokens) | $19.50 | $6.73 |
| Provenance | Runs in:USMade in:United States | Runs in:USMade in:United States |
Quality by category
Win rate per category: how often each model beats a field-average model on a prompt from that category. 50% is average. It is not a percentage of correct answers.
| Category | Claude Sonnet 4.6 | gpt-5.4-mini |
|---|---|---|
| coding | 55.8% | 72.1% |
| creative | 53.3% | 85.8% |
| factual | 63.5% | 54.0% |
| multilingual | 53.1% | 61.8% |
| reasoning | 67.6% | 63.1% |
Anthropic
Full review of Claude Sonnet 4.6 →
OpenAI
Full review of gpt-5.4-mini →