Side-by-side comparison of GPT-4o mini (OpenAI) and Claude 3.5 Haiku (Anthropic) — benchmarks, pricing, and capabilities.
| GPT-4o mini OpenAI | Claude 3.5 Haiku Anthropic | |
|---|---|---|
| Category | LLMs | LLMs |
| Specifications | ||
| Context Window | 128K | 200K |
| Pricing (per 1M tokens) | ||
| Input Cost | $0.15 | $0.80 |
| Output Cost | $0.60 | $4.00 |
| Performance | ||
| Overall Score | 85.0 | 84.0 |
| ARC-Challenge | 95.1 | — |
| BigBench Hard | 76.2 | 78.0 |
| Chatbot Arena ELO | 1138.0 | — |
| DROP | 76.8 | — |
| GSM8K | 86.1 | 86.5 |
| HumanEval | 78.5 | 80.5 |
| MATH | 62.0 | 65.0 |
| MMLU | 80.2 | 81.5 |
| TruthfulQA | 58.5 | — |
| WinoGrande | 89.7 | — |
| Community | ||
| User Rating | ★ 4.5 | ★ 4.4 |
| Reviews | 2100 | 290 |