Gemini 3.5 Flash vs Gemini 3 Flash Preview
Gemini 3.5 Flash vs Gemini 3 Flash Preview: which AI model is cheaper, has the larger context window and more capabilities? Side-by-side comparison updated daily.
Quick verdict
- Gemini 3 Flash Preview is 3.0× cheaper than Gemini 3.5 Flash for the same mix of input and output tokens.
- Both have the same context window.
- Gemini 3.5 Flash is the more recent release (May 19, 2026).
- Gemini 3.5 Flash scores higher on independent tests (overall index 154.6 vs 151.8).
- Choose Gemini 3 Flash Preview if cost matters most; choose Gemini 3.5 Flash if you need its specific strengths above. For the best results, test both on your own prompts.
| Gemini 3.5 Flash | Gemini 3 Flash Preview | |
|---|---|---|
| Company | Google DeepMind | Google DeepMind |
| Released | May 19, 2026 ● | Dec 17, 2025 |
| Overall index | 154.6 ● | 151.8 |
| SWE-bench Verified | 79.3% ● | 75.4% |
| GPQA Diamond | 92.8% ● | 89.4% |
| AIME math | 95.6% | 95.6% |
| FrontierMath | 62.8% ● | 51.2% |
| SimpleQA Verified | 66.2% | 66.8% ● |
| Input (per 1M tokens) | $1.50 | $0.50 ● |
| Output (per 1M tokens) | $9 | $3 ● |
| Cost for 1M input + 1M output tokens | $10.50 | $3.50 ● |
| Providers | 7 ● | 6 |
| Context | 1M | 1M |
| Max output | 64K | 64K |
| Inputs | Text, Image, Video, Files, Audio | Text, Image, Files, Audio, Video |
| Outputs | Text | Text |
| Reasoning | ✓ | ✓ |
| Tool use | ✓ | ✓ |
| Structured output | ✓ | ✓ |
| Open weights | — | — |