Gemma 4 12B vs North Mini Code: Benchmarks, Pricing & Capabilities Compared
TL;DR — Gemma 4 12B wins for general use · North Mini Code wins for long-context.
Gemma 4 12B Google
- Released
- 2026-06-03
- Context window
- 131K tokens
- Input price
- $0.00 / Mtok
- Output price
- $0.00 / Mtok
North Mini Code Cohere
- Released
- 2026-06-09
- Context window
- 256K tokens
- Input price
- $0.00 / Mtok
- Output price
- $0.00 / Mtok
Benchmark comparison
| Benchmark | Gemma 4 12B | North Mini Code |
|---|---|---|
| AA Intelligence Index | 29.2 ✓ | 27.6 |
| GPQA Diamond | 75.3% | 75.7% ✓ |
| HLE | 14.8% ✓ | 9.9% |
| IF-Bench | 73.5% ✓ | 57.6% |
| LiveCodeBench Reasoning | 55.3% ✓ | 32.3% |
| SciCode | 38.2% | 38.2% |
| TAU2-bench | 36.3% | 37.4% ✓ |
| TerminalBench-Hard | 18.2% | 31.1% ✓ |
Pricing comparison
| Metric | Gemma 4 12B | North Mini Code |
|---|---|---|
| Input ($/Mtok) | $0.00 | $0.00 |
| Output ($/Mtok) | $0.00 | $0.00 |
| Cached input ($/Mtok) | — | — |
| Cost per 1M-token roundtrip (1M in + 1M out) | $0.00 | $0.00 |
Context window & modalities
| Attribute | Gemma 4 12B | North Mini Code |
|---|---|---|
| Context window | 131K tokens | 256K tokens |
| Input modalities | text, image, video | text |
| Output modalities | text | text |
| Knowledge cutoff | — | — |
Verdict by use case
Coding
Insufficient data
Basis: SWE-bench
No shared coding benchmark.
Reasoning
→ North Mini Code
Basis: GPQA Diamond
Gemma 4 12B 75.3% vs North Mini Code 75.7% on GPQA Diamond.
Math
Insufficient data
Basis: MATH / AIME
No shared math benchmark.
Long context
→ North Mini Code
Basis: Context window
Gemma 4 12B 131K tokens vs North Mini Code 256K tokens.
Cost
Tie
Basis: Input $/Mtok
Gemma 4 12B $0/Mtok vs North Mini Code $0/Mtok input.
Changelog & releases
Gemma 4 12B
Released 2026-06-03
North Mini Code
Released 2026-06-09