token.app › Compare › GPT-5 Nano vs Gemini 3.5 Flash Lite
GPT-5 Nano vs Gemini 3.5 Flash Lite
GPT-5 Nano and Gemini 3.5 Flash Lite split the 4 shared benchmarks evenly. GPT-5 Nano is 6.2× cheaper per token on a blended 3:1 basis. Gemini 3.5 Flash Lite accepts the larger context window (1.0M).
Head to head
Blended price uses a 3:1 input:output mix
| GPT-5 Nano | Gemini 3.5 Flash Lite | |
|---|---|---|
| Provider | OpenAI | |
| Input $/1M | $0.050 | $0.300 |
| Output $/1M | $0.400 | $2.50 |
| Blended $/1M | $0.138 | $0.850 |
| Context window | 400K | 1.0M |
| Max output | 128K | 66K |
| Released | Aug 2025 | Jul 2026 |
| Licence | Proprietary | Proprietary |
| GPQA Diamond | 69.4% | 83.3% |
| FrontierMath T1–3 | 20.0% | 26.0% |
| FrontierMath T4 | 2.4% | 0.0% |
| OTIS Mock AIME | 81.1% | 71.1% |
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 GPT-5 Nano if…
- Costs less per token — $0.138 vs $0.850 blended
- Higher FrontierMath T4 (2.4% vs 0.0%)
- Higher OTIS Mock AIME (81.1% vs 71.1%)
Choose Gemini 3.5 Flash Lite if…
- Higher GPQA Diamond (83.3% vs 69.4%)
- Higher FrontierMath T1–3 (26.0% vs 20.0%)
- Larger context window (1.0M)
- Newer model (released Jul 2026)
FAQ
Which is better, GPT-5 Nano or Gemini 3.5 Flash Lite?
Across the 4 benchmarks both models have independently-run scores for, GPT-5 Nano leads on 2 and Gemini 3.5 Flash Lite leads on 2. Benchmarks are one input — price and context window are on this page too.
Is GPT-5 Nano cheaper than Gemini 3.5 Flash Lite?
GPT-5 Nano is cheaper: $0.138 versus $0.850 per million tokens blended at 3:1 input:output. Input alone: $0.050 vs $0.300. Output alone: $0.400 vs $2.50.
What context windows do GPT-5 Nano and Gemini 3.5 Flash Lite have?
GPT-5 Nano: 400,000 tokens. Gemini 3.5 Flash Lite: 1,048,576 tokens.
Who makes GPT-5 Nano and Gemini 3.5 Flash Lite?
GPT-5 Nano is made by OpenAI. Gemini 3.5 Flash Lite is made by Google.