Side-by-side comparison of GPT-4o (OpenAI) and StarCoder 2 15B (BigCode) — benchmarks, pricing, and capabilities.
| GPT-4o OpenAI | StarCoder 2 15B BigCode | |
|---|---|---|
| Category | LLMs | Code Models |
| Specifications | ||
| Context Window | 128K | 16K |
| Pricing (per 1M tokens) | ||
| Input Cost | $2.50 | — |
| Output Cost | $10.00 | — |
| Performance | ||
| Overall Score | 92.5 | 72.0 |
| ARC-Challenge | 96.9 | — |
| BigBench Hard | 87.2 | — |
| Chatbot Arena ELO | 1270.0 | — |
| DROP | 88.1 | — |
| GSM8K | 95.3 | — |
| HumanEval | 92.0 | 44.2 |
| MATH | 76.6 | — |
| MBPP | — | 64.5 |
| MMLU | 88.7 | — |
| TruthfulQA | 72.2 | — |
| WinoGrande | 89.6 | — |
| Community | ||
| User Rating | ★ 4.7 | ★ 4.0 |
| Reviews | 1240 | 180 |