Side-by-side comparison of GPT-o1 (OpenAI) and Claude 3.5 Haiku (Anthropic) — benchmarks, pricing, and capabilities.
| GPT-o1 OpenAI | Claude 3.5 Haiku Anthropic | |
|---|---|---|
| Category | LLMs | LLMs |
| Specifications | ||
| Context Window | 200K | 200K |
| Pricing (per 1M tokens) | ||
| Input Cost | $15.00 | $0.80 |
| Output Cost | $60.00 | $4.00 |
| Performance | ||
| Overall Score | 93.5 | 84.0 |
| BigBench Hard | 90.5 | 78.0 |
| DROP | 90.2 | — |
| GSM8K | 97.8 | 86.5 |
| HumanEval | 92.4 | 80.5 |
| MATH | 94.8 | 65.0 |
| MMLU | 91.8 | 81.5 |
| TruthfulQA | 74.5 | — |
| Community | ||
| User Rating | ★ 4.6 | ★ 4.4 |
| Reviews | 520 | 290 |