token.app › Compare › Mistral Medium 3 vs Gemma 4 31B
Mistral Medium 3 vs Gemma 4 31B
Gemma 4 31B leads on 2 of 2 shared benchmarks. Gemma 4 31B is 5.0× cheaper per token on a blended 3:1 basis. Gemma 4 31B accepts the larger context window (262K).
Head to head
Blended price uses a 3:1 input:output mix
| Mistral Medium 3 | Gemma 4 31B | |
|---|---|---|
| Provider | Mistral AI | |
| Input $/1M | $0.400 | $0.100 |
| Output $/1M | $2.00 | $0.340 |
| Blended $/1M | $0.800 | $0.160 |
| Context window | 131K | 262K |
| Max output | — | 262K |
| Released | May 2025 | Apr 2026 |
| Licence | Proprietary | Open weights |
| GPQA Diamond | 59.5% | 75.8% |
| OTIS Mock AIME | 32.2% | 73.3% |
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 Mistral Medium 3 if…
- No clear advantage on the data we hold.
Choose Gemma 4 31B if…
- Costs less per token — $0.160 vs $0.800 blended
- Higher GPQA Diamond (75.8% vs 59.5%)
- Higher OTIS Mock AIME (73.3% vs 32.2%)
- Larger context window (262K)
- Open weights — self-hostable
- Newer model (released Apr 2026)
FAQ
Which is better, Mistral Medium 3 or Gemma 4 31B?
Across the 2 benchmarks both models have independently-run scores for, Mistral Medium 3 leads on 0 and Gemma 4 31B leads on 2. Benchmarks are one input — price and context window are on this page too.
Is Mistral Medium 3 cheaper than Gemma 4 31B?
Gemma 4 31B is cheaper: $0.160 versus $0.800 per million tokens blended at 3:1 input:output. Input alone: $0.400 vs $0.100. Output alone: $2.00 vs $0.340.
What context windows do Mistral Medium 3 and Gemma 4 31B have?
Mistral Medium 3: 131,072 tokens. Gemma 4 31B: 262,144 tokens.
Who makes Mistral Medium 3 and Gemma 4 31B?
Mistral Medium 3 is made by Mistral AI. Gemma 4 31B is made by Google.
Related comparisons