token.app › Compare › DeepSeek V3 0324 vs Gemma 4 31B
DeepSeek V3 0324 vs Gemma 4 31B
Gemma 4 31B leads on 2 of 2 shared benchmarks. Gemma 4 31B is 2.0× 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
| DeepSeek V3 0324 | Gemma 4 31B | |
|---|---|---|
| Provider | DeepSeek | |
| Input $/1M | $0.290 | $0.200 |
| Output $/1M | $1.14 | $0.400 |
| Blended $/1M | $0.502 | $0.250 |
| Context window | 164K | 262K |
| Max output | 115K | 16K |
| Released | Mar 2025 | Apr 2026 |
| Licence | Open weights | Open weights |
| GPQA Diamond | 67.6% | 75.8% |
| OTIS Mock AIME | 37.8% | 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 DeepSeek V3 0324 if…
- No clear advantage on the data we hold.
Choose Gemma 4 31B if…
- Costs less per token — $0.250 vs $0.502 blended
- Higher GPQA Diamond (75.8% vs 67.6%)
- Higher OTIS Mock AIME (73.3% vs 37.8%)
- Larger context window (262K)
- Newer model (released Apr 2026)
FAQ
Which is better, DeepSeek V3 0324 or Gemma 4 31B?
Across the 2 benchmarks both models have independently-run scores for, DeepSeek V3 0324 leads on 0 and Gemma 4 31B leads on 2. Benchmarks are one input — price and context window are on this page too.
Is DeepSeek V3 0324 cheaper than Gemma 4 31B?
Gemma 4 31B is cheaper: $0.250 versus $0.502 per million tokens blended at 3:1 input:output. Input alone: $0.290 vs $0.200. Output alone: $1.14 vs $0.400.
What context windows do DeepSeek V3 0324 and Gemma 4 31B have?
DeepSeek V3 0324: 163,840 tokens. Gemma 4 31B: 262,144 tokens.
Who makes DeepSeek V3 0324 and Gemma 4 31B?
DeepSeek V3 0324 is made by DeepSeek. Gemma 4 31B is made by Google.
Related comparisons