Side-by-side comparison of Qwen 2.5 Coder 32B (Alibaba) and Gemini 1.5 Pro (Google) — benchmarks, pricing, and capabilities.
| Qwen 2.5 Coder 32B Alibaba | Gemini 1.5 Pro Google | |
|---|---|---|
| Category | Code Models | LLMs |
| Specifications | ||
| Context Window | 128K | 1.0M |
| Pricing (per 1M tokens) | ||
| Input Cost | — | $1.25 |
| Output Cost | — | $5.00 |
| Performance | ||
| Overall Score | 88.0 | 90.8 |
| ARC-Challenge | — | 89.5 |
| BigBench Hard | — | 85.1 |
| Chatbot Arena ELO | — | 1126.0 |
| DROP | — | 85.8 |
| GSM8K | — | 79.4 |
| HumanEval | 92.7 | 89.1 |
| LiveCodeBench | 42.8 | — |
| MATH | — | 74.0 |
| MBPP | 90.2 | — |
| MMLU | — | 86.4 |
| SWE-bench Verified | 33.5 | — |
| TruthfulQA | — | 69.8 |
| WinoGrande | — | 84.2 |
| Community | ||
| User Rating | ★ 4.5 | ★ 4.5 |
| Reviews | 175 | 654 |