Gemini 3.5 Flash vs Kimi K3
Gemini 3.5 Flash vs Kimi K3: which AI model is cheaper, has the larger context window and more capabilities? Side-by-side comparison updated daily.
Quick verdict
- Gemini 3.5 Flash is 1.8× cheaper than Kimi K3 for the same mix of input and output tokens.
- Both have the same context window.
- Kimi K3 is the more recent release (Jul 16, 2026).
- Only Kimi K3 has openly published weights you can run yourself.
- Kimi K3 scores higher on independent tests (overall index 157.7 vs 154.6).
- Choose Gemini 3.5 Flash if cost matters most; choose Kimi K3 if you need its specific strengths above. For the best results, test both on your own prompts.
| Gemini 3.5 Flash | Kimi K3 | |
|---|---|---|
| Company | Google DeepMind | Moonshot AI |
| Released | May 19, 2026 | Jul 16, 2026 ● |
| Overall index | 154.6 | 157.7 ● |
| SWE-bench Verified | 79.3% | — |
| GPQA Diamond | 92.8% | 93.1% ● |
| AIME math | 95.6% | 97.2% ● |
| FrontierMath | 62.8% | 72.2% ● |
| SimpleQA Verified | 66.2% ● | 50.6% |
| Input (per 1M tokens) | $1.50 ● | $3 |
| Output (per 1M tokens) | $9 ● | $15 |
| Cost for 1M input + 1M output tokens | $10.50 ● | $18.00 |
| Providers | 7 | 22 ● |
| Context | 1M | 1M |
| Max output | 64K | 944K ● |
| Inputs | Text, Image, Video, Files, Audio ● | Text, Image, Video |
| Outputs | Text | Text |
| Reasoning | ✓ | ✓ |
| Tool use | ✓ | ✓ |
| Structured output | ✓ | ✓ |
| Open weights | — | ✓ |