Side-by-side comparison of Whisper Large v3 (OpenAI) and Gemini 2.0 Flash (Google) — benchmarks, pricing, and capabilities.
| Whisper Large v3 OpenAI | Gemini 2.0 Flash Google | |
|---|---|---|
| Category | Audio & Speech | LLMs |
| Specifications | ||
| Context Window | — | 1.0M |
| Pricing (per 1M tokens) | ||
| Input Cost | — | $0.10 |
| Output Cost | — | $0.40 |
| Performance | ||
| Overall Score | 92.0 | 89.5 |
| GSM8K | — | 93.8 |
| HumanEval | — | 89.5 |
| MATH | — | 78.2 |
| MMLU | — | 86.8 |
| WER (inverted) | 94.5 | — |
| Community | ||
| User Rating | ★ 4.7 | ★ 4.5 |
| Reviews | 1560 | 410 |