Compare AI models
Claude Opus 4.8vsgpt-5.4-mini
Which should you pick?
- gpt-5.4-mini · overall 64.6 vs 58.9
- gpt-5.4-mini cheaper output · $6.73 vs $32.50 /1M
Specifications
| Claude Opus 4.8 | gpt-5.4-mini | |
|---|---|---|
| Tier | A | A |
| Context window | 1.0M tokens | — |
| Input price (per 1M tokens) | $6.50 | $1.13 |
| Output price (per 1M tokens) | $32.50 | $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 Opus 4.8 | gpt-5.4-mini |
|---|---|---|
| coding | 50.2% | 73.2% |
| creative | 38.4% | 85.6% |
| factual | 69.9% | 56.4% |
| multilingual | 61.5% | 61.8% |
| reasoning | 68.7% | 65.4% |
Anthropic
Full review of Claude Opus 4.8 →
OpenAI
Full review of gpt-5.4-mini →