token.app › Compare › Gemma 4 31B vs DeepSeek V4 Flash 0731
Gemma 4 31B vs DeepSeek V4 Flash 0731
DeepSeek V4 Flash 0731 leads on 3 of 3 shared benchmarks. DeepSeek V4 Flash 0731 is 1.4× cheaper per token on a blended 3:1 basis. DeepSeek V4 Flash 0731 accepts the larger context window (1.0M).
Head to head
Blended price uses a 3:1 input:output mix
| Gemma 4 31B | DeepSeek V4 Flash 0731 | |
|---|---|---|
| Provider | DeepSeek | |
| Input $/1M | $0.100 | $0.090 |
| Output $/1M | $0.340 | $0.180 |
| Blended $/1M | $0.160 | $0.113 |
| Context window | 262K | 1.0M |
| Max output | 262K | 384K |
| Released | Apr 2026 | Jul 2026 |
| Licence | Open weights | Open weights |
| GPQA Diamond | 75.8% | 91.0% |
| SimpleQA Verified | 9.6% | 34.7% |
| OTIS Mock AIME | 73.3% | 94.4% |
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 Gemma 4 31B if…
- No clear advantage on the data we hold.
Choose DeepSeek V4 Flash 0731 if…
- Costs less per token — $0.113 vs $0.160 blended
- Higher GPQA Diamond (91.0% vs 75.8%)
- Higher SimpleQA Verified (34.7% vs 9.6%)
- Higher OTIS Mock AIME (94.4% vs 73.3%)
- Larger context window (1.0M)
- Newer model (released Jul 2026)
FAQ
Which is better, Gemma 4 31B or DeepSeek V4 Flash 0731?
Across the 3 benchmarks both models have independently-run scores for, Gemma 4 31B leads on 0 and DeepSeek V4 Flash 0731 leads on 3. Benchmarks are one input — price and context window are on this page too.
Is Gemma 4 31B cheaper than DeepSeek V4 Flash 0731?
DeepSeek V4 Flash 0731 is cheaper: $0.113 versus $0.160 per million tokens blended at 3:1 input:output. Input alone: $0.100 vs $0.090. Output alone: $0.340 vs $0.180.
What context windows do Gemma 4 31B and DeepSeek V4 Flash 0731 have?
Gemma 4 31B: 262,144 tokens. DeepSeek V4 Flash 0731: 1,048,576 tokens.
Who makes Gemma 4 31B and DeepSeek V4 Flash 0731?
Gemma 4 31B is made by Google. DeepSeek V4 Flash 0731 is made by DeepSeek.