token.app › Compare › GPT-3.5 Turbo vs Mistral Nemo
GPT-3.5 Turbo vs Mistral Nemo
Mistral Nemo leads on 1 of 1 shared benchmarks. Mistral Nemo is 34× cheaper per token on a blended 3:1 basis. Mistral Nemo accepts the larger context window (131K).
Head to head
Blended price uses a 3:1 input:output mix
| GPT-3.5 Turbo | Mistral Nemo | |
|---|---|---|
| Provider | OpenAI | Mistral AI |
| Input $/1M | $0.500 | $0.019 |
| Output $/1M | $1.50 | $0.030 |
| Blended $/1M | $0.750 | $0.022 |
| Context window | 16K | 131K |
| Max output | 4K | 16K |
| Released | May 2023 | Jul 2024 |
| Licence | Proprietary | Open weights |
| GPQA Diamond | 27.2% | 29.9% |
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-3.5 Turbo if…
- No clear advantage on the data we hold.
Choose Mistral Nemo if…
- Costs less per token — $0.022 vs $0.750 blended
- Higher GPQA Diamond (29.9% vs 27.2%)
- Larger context window (131K)
- Open weights — self-hostable
- Newer model (released Jul 2024)
FAQ
Which is better, GPT-3.5 Turbo or Mistral Nemo?
Across the 1 benchmark both models have independently-run scores for, GPT-3.5 Turbo leads on 0 and Mistral Nemo leads on 1. Benchmarks are one input — price and context window are on this page too.
Is GPT-3.5 Turbo cheaper than Mistral Nemo?
Mistral Nemo is cheaper: $0.022 versus $0.750 per million tokens blended at 3:1 input:output. Input alone: $0.500 vs $0.019. Output alone: $1.50 vs $0.030.
What context windows do GPT-3.5 Turbo and Mistral Nemo have?
GPT-3.5 Turbo: 16,385 tokens. Mistral Nemo: 131,072 tokens.
Who makes GPT-3.5 Turbo and Mistral Nemo?
GPT-3.5 Turbo is made by OpenAI. Mistral Nemo is made by Mistral AI.