Models / Compare /DeepSeek V4 Pro vs Gemma 4 31B
Head to head
DeepSeek V4 Pro vs Gemma 4 31B
Compared on live catalog data — pricing synced daily, benchmark scores with provenance.
The short version
- Gemma 4 31B is cheaper to run hosted: $0.34/M output vs $0.87/M for DeepSeek V4 Pro (2.6× difference at the cheapest tracked provider).
- DeepSeek V4 Pro takes 1M tokens of context vs 262K for Gemma 4 31B.
- DeepSeek V4 Pro scores -0.0078 on Arena Agent (IPS) vs -0.161 for Gemma 4 31B.
- DeepSeek V4 Pro scores 1502.1991 on Arena Coding vs 1498.1274 for Gemma 4 31B.
| Spec | ||
|---|---|---|
| Vendor | DeepSeek | |
| Parameters | 1.6T / 37B | 32.7B |
| 1M | 262K | |
| Weights | OPEN | OPEN |
| License | MIT License | Apache License 2.0 |
| Modality | text->text | text+image+video->text |
| Released | Apr 22, 2026 | Mar 11, 2026 |
| 1008 GBest | 20.6 GBest | |
| Cheapest hosted | $0.43 / $0.87 per 1M (OpenRouter) | $0.10 / $0.34 per 1M (OpenRouter) |
| Tracked providers | 23 | 22 |
DeepSeek V4 Pro — our take
DeepSeek V4 Pro is a large downloadable text model with a one-million-token request limit and a permissive MIT licence. It excels at coding and hard-prompt tasks on the independent leaderboards we track, though its creative-writing score lags behind its other skills.
full breakdown →Gemma 4 31B — our take
Gemma 4 is a 32.7-billion-parameter text, image and video model from Google with a permissive Apache licence. It scores consistently across six Arena categories, with coding as its relative standout, and is available from ten hosts with a wide spread in price and speed.
full breakdown →Need more columns? Use theinteractive comparison to add up to four models.