Gemma 3 12B Instruct vs Qwen3.6 Max
Google vs Alibaba — benchmarks, pricing, and capabilities side by side.
- •Qwen3.6 Max has the higher intelligence index (88.8 vs 40)
- •Gemma 3 12B Instruct is cheaper ($0.10 vs $1.04 per 1M input)
| Gemma 3 12B Instruct | Qwen3.6 Max | |
|---|---|---|
| Intelligence index | 40 | 88.8 |
| Developer | Alibaba | |
| Type | LLM | LLM |
| Access | — | API only |
| Context window | — | 262,144 tokens |
| Input price | $0.10 / 1M | $1.04 / 1M |
| Output price | $0.30 / 1M | $6.24 / 1M |
| Speed | — | 36 tok/s |
| Released | March 12, 2025 | April 27, 2026 |
| Parameters | — | — |
| Input modalities | — | Text |
| Output modalities | — | Text |
Shared benchmarks
Gemma 3 12B Instruct
Qwen3.6 Max
GPQA Diamond
34.9
88.8
Humanity’s Last Exam
4.8
28.9