token.app › Compare › Gemini 3.5 Flash vs Kimi K3
Gemini 3.5 Flash vs Kimi K3
Kimi K3 leads on 4 of 5 shared benchmarks. Gemini 3.5 Flash is 1.8× cheaper per token on a blended 3:1 basis.
Head to head
Blended price uses a 3:1 input:output mix
| Gemini 3.5 Flash | Kimi K3 | |
|---|---|---|
| Provider | Moonshot AI | |
| Input $/1M | $1.50 | $3.00 |
| Output $/1M | $9.00 | $15.00 |
| Blended $/1M | $3.38 | $6.00 |
| Context window | 1.0M | 1.0M |
| Max output | 66K | — |
| Released | May 2026 | Jul 2026 |
| Licence | Proprietary | Open weights |
| GPQA Diamond | 92.8% | 93.1% |
| FrontierMath T1–3 | 62.8% | 72.2% |
| FrontierMath T4 | 26.8% | 39.0% |
| SimpleQA Verified | 68.4% | 42.7% |
| OTIS Mock AIME | 95.6% | 97.2% |
Benchmark scores independently run and published by Epoch AI, 'AI Benchmarking Hub', used under CC BY 4.0. Only benchmarks with a score for BOTH models are compared.
Choose Gemini 3.5 Flash if…
- Costs less per token — $3.38 vs $6.00 blended
- Higher SimpleQA Verified (68.4% vs 42.7%)
Choose Kimi K3 if…
- Higher GPQA Diamond (93.1% vs 92.8%)
- Higher FrontierMath T1–3 (72.2% vs 62.8%)
- Higher FrontierMath T4 (39.0% vs 26.8%)
- Higher OTIS Mock AIME (97.2% vs 95.6%)
- Open weights — self-hostable
- Newer model (released Jul 2026)
FAQ
Which is better, Gemini 3.5 Flash or Kimi K3?
Across the 5 benchmarks both models have independently-run scores for, Gemini 3.5 Flash leads on 1 and Kimi K3 leads on 4. Benchmarks are one input — price and context window are on this page too.
Is Gemini 3.5 Flash cheaper than Kimi K3?
Gemini 3.5 Flash is cheaper: $3.38 versus $6.00 per million tokens blended at 3:1 input:output. Input alone: $1.50 vs $3.00. Output alone: $9.00 vs $15.00.
What context windows do Gemini 3.5 Flash and Kimi K3 have?
Gemini 3.5 Flash: 1,048,576 tokens. Kimi K3: 1,048,576 tokens.
Who makes Gemini 3.5 Flash and Kimi K3?
Gemini 3.5 Flash is made by Google. Kimi K3 is made by Moonshot AI.
Related comparisons