Gemma 4 12B vs Qwen3.7 Plus: Benchmarks, Pricing & Capabilities Compared
TL;DR — Gemma 4 12B wins for general use · Qwen3.7 Plus wins for reasoning + long-context.
Gemma 4 12B Google
- Released
- 2026-06-03
- Context window
- 131K tokens
- Input price
- $0.00 / Mtok
- Output price
- $0.00 / Mtok
Qwen3.7 Plus Alibaba
- Released
- 2026-06-01
- Context window
- 1M tokens
- Input price
- $0.40 / Mtok
- Output price
- $1.16 / Mtok
Benchmark comparison
| Benchmark | Gemma 4 12B | Qwen3.7 Plus |
|---|---|---|
| AA Intelligence Index | 29.0 | 53.3 ✓ |
| GPQA Diamond | 75.3% | 90.0% ✓ |
| HLE | 14.6% | 33.4% ✓ |
| IF-Bench | 73.5% | 78.0% ✓ |
| LiveCodeBench Reasoning | 55.3% | 65.0% ✓ |
| SciCode | 38.2% | 45.5% ✓ |
| TAU2-bench | 34.8% | 93.0% ✓ |
| TerminalBench-Hard | 18.2% | 47.0% ✓ |
Pricing comparison
| Metric | Gemma 4 12B | Qwen3.7 Plus |
|---|---|---|
| Input ($/Mtok) | $0.00 | $0.40 |
| Output ($/Mtok) | $0.00 | $1.16 |
| Cached input ($/Mtok) | — | — |
| Cost per 1M-token roundtrip (1M in + 1M out) | $0.00 | $1.56 |
Context window & modalities
| Attribute | Gemma 4 12B | Qwen3.7 Plus |
|---|---|---|
| Context window | 131K tokens | 1M tokens |
| Input modalities | text, image, video | text, image, video |
| Output modalities | text | text |
| Knowledge cutoff | — | — |
Verdict by use case
Coding
Insufficient data
Basis: SWE-bench
No shared coding benchmark.
Reasoning
→ Qwen3.7 Plus
Basis: GPQA Diamond
Gemma 4 12B 75.3% vs Qwen3.7 Plus 90% on GPQA Diamond.
Math
Insufficient data
Basis: MATH / AIME
No shared math benchmark.
Long context
→ Qwen3.7 Plus
Basis: Context window
Gemma 4 12B 131K tokens vs Qwen3.7 Plus 1M tokens.
Cost
→ Gemma 4 12B
Basis: Input $/Mtok
Gemma 4 12B $0/Mtok vs Qwen3.7 Plus $0.4/Mtok input.
Changelog & releases
Gemma 4 12B
Released 2026-06-03
Qwen3.7 Plus
Released 2026-06-01