Side-by-side comparison of Claude 3 Haiku (Anthropic) and GPT-4o mini (OpenAI) — benchmarks, pricing, and capabilities.
| Claude 3 Haiku Anthropic | GPT-4o mini OpenAI | |
|---|---|---|
| Category | LLMs | LLMs |
| Specifications | ||
| Context Window | 200K | 128K |
| Pricing (per 1M tokens) | ||
| Input Cost | $0.25 | $0.15 |
| Output Cost | $1.25 | $0.60 |
| Performance | ||
| Overall Score | 82.3 | 85.0 |
| ARC-Challenge | 85.2 | 90.4 |
| BigBench Hard | 72.1 | 76.2 |
| Chatbot Arena ELO | 1241.0 | 1191.0 |
| DROP | 72.5 | 76.8 |
| GSM8K | 65.9 | 86.1 |
| HumanEval | 75.0 | 78.5 |
| MATH | 58.2 | 62.0 |
| MMLU | 77.3 | 80.2 |
| TruthfulQA | 54.2 | 78.2 |
| WinoGrande | 83.9 | 80.2 |
| Community | ||
| User Rating | ★ 4.4 | ★ 4.5 |
| Reviews | 567 | 2100 |