Gemma 3 vs North Mini Code
Pricing, benchmarks, and use case comparison
Quick take
- •Gemma 3 is meaningfully stronger at multimodal (70 vs 5 on our capability index).
- •North Mini Code is meaningfully stronger at coding (78 vs 62).
- •Gemma 3 is open-weights (free to self-host); North Mini Code is paid API only.
- •North Mini Code has a 256K tokens context window vs 128K tokens (32K for the 1B variant) - better for whole-repo or long-document work.
Specs comparison
| Gemma 3 | North Mini Code | |
|---|---|---|
| Provider | Google DeepMind | Cohere |
| Type | Open source | Closed source |
| Context window | 128K tokens (32K for the 1B variant) | ✓256K tokens |
| Input / 1M tokens | ✓Free (self-host) | 0 |
| Output / 1M tokens | Free (self-host) | 0 |
| Release date | 2025-03 | 2026-06 |
Benchmarks
| Benchmark | Gemma 3 | North Mini Code |
|---|---|---|
| MATH (27B) | 89% | - |
| MMMU (27B, multimodal) | 64.9% | - |
| Artificial Analysis Coding Index | - | 33.4 |
| Throughput vs Devstral Small 2 | - | Up to 2.8x higher output throughput |
Scores sourced from official provider release posts and independent benchmark aggregators.
Which should you choose?
Choose Gemma 3 if...
- →You need an open, self-hostable model with a size to match your hardware
- →Multilingual or multimodal tasks on-prem
- →Privacy-sensitive or offline deployments
- →Fine-tuning on your own data
Choose North Mini Code if...
- →You want a self-hostable, sovereign coding agent on modest hardware
- →You run agentic SWE workflows (repo edits, sub-agent orchestration, code review)
- →You need terminal/tool-driven multi-turn agents
- →You want high coding throughput at low compute cost