Model comparison
Gemma 3 12B vs Qwen3.7 Max
Qwen3.7 Max is the stronger model overall, scoring 51.4 to 31.8 on the Noometry Index. Gemma 3 12B costs 50× less per token, which makes it the better buy when Qwen3.7 Max's lead doesn't matter for your workload.
Last verified . 19 shared benchmarks.
Google
Alibaba (Qwen)Summary
- They share 19 benchmarks with published results for both. Gemma 3 12B scores higher in 1 category and Qwen3.7 Max in 8 categories; 9 gaps are clear of the uncertainty.
- The widest gap is in math, where Qwen3.7 Max leads 62.3 to 21.0.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 16.7% for Gemma 3 12B and 95.6% for Qwen3.7 Max.
- Gemma 3 12B is cheaper at $0.05 / $0.15 per million input/output tokens, against $2.50 / $7.50 for Qwen3.7 Max.
- Qwen3.7 Max accepts more context: 1M tokens versus 131K.
- Gemma 3 12B has downloadable open weights; the other is API-only.
Side by side
| Gemma 3 12B | Qwen3.7 Max | |
|---|---|---|
| Provider | Alibaba (Qwen) | |
| Noometry Index | 31.8 | 51.4 |
| Released | 2025-03-12 | 2026-05-19 |
| Weights | Open | Proprietary |
| Context window | 131K | 1M |
| Max output | 8K | 131K |
| Input $ / M tokens | $0.05 | $2.50 |
| Output $ / M tokens | $0.15 | $7.50 |
| Results tracked | 24 | 33 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Qwen3.7 Max leads
Gemma 3 12B: 31.2 (#276), Qwen3.7 Max: 50.2 (#43)
| Benchmark | Gemma 3 12B | Qwen3.7 Max |
|---|---|---|
| SciCode | 17.4% | 48.8% |
| LMArena Coding | 1281 | 1498 |
| SWE-bench Verified | — | 77.3% |
| LMArena WebDev | — | 1515 |
| ALE-Bench | — | 1,189 |
Agentic & Tool Use Gemma 3 12B leads
Gemma 3 12B: 25.3 (#101), Qwen3.7 Max: 21.8 (#129)
| Benchmark | Gemma 3 12B | Qwen3.7 Max |
|---|---|---|
| Berkeley Function Calling Leaderboard | 30.4% | — |
| GBAEval | — | 0.4% |
Reasoning Qwen3.7 Max leads
Gemma 3 12B: 15.2 (#307), Qwen3.7 Max: 48.4 (#36)
| Benchmark | Gemma 3 12B | Qwen3.7 Max |
|---|---|---|
| CritPt | 0% | 13.4% |
| Chess Puzzles | 0% | 19% |
| LMArena Hard Prompts | 1309 | 1483 |
| DTBench | 48.8% | 92.3% |
| LMCA | 4.5% | 44% |
| Epoch Capabilities Index | 123.49 | 153.74 |
| SimpleBench | — | 70.4% |
| NYT Connections (extended) | — | 85.1% |
| EBR-Bench | — | 9.5% |
| Mystery Game Puzzles | — | 32% |
Math Qwen3.7 Max leads
Gemma 3 12B: 21.0 (#273), Qwen3.7 Max: 62.3 (#26)
| Benchmark | Gemma 3 12B | Qwen3.7 Max |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 16.7% | 95.6% |
| LMArena Math | 1307 | 1488 |
| FrontierMath (Tiers 1-3) | — | 64.6% |
| FrontierMath Tier 4 | — | 34.1% |
| ProofBench | — | 26% |
Knowledge Qwen3.7 Max leads
Gemma 3 12B: 26.5 (#250), Qwen3.7 Max: 61.7 (#24)
| Benchmark | Gemma 3 12B | Qwen3.7 Max |
|---|---|---|
| GPQA Diamond | 39.5% | 90.9% |
| LMArena Expert | 1248 | 1488 |
| SimpleQA Verified | — | 55.8% |
| Vectara Hallucination Rate | 4.4% | — |
Multimodal Not comparable
Gemma 3 12B: —, Qwen3.7 Max: —
| Benchmark | Gemma 3 12B | Qwen3.7 Max |
|---|---|---|
| MindCube | 46.7% | — |
Multilingual Qwen3.7 Max leads
Gemma 3 12B: 45.9 (#160), Qwen3.7 Max: 57.1 (#13)
| Benchmark | Gemma 3 12B | Qwen3.7 Max |
|---|---|---|
| LMArena Non-English | 1318 | 1475 |
| LMArena Russian | 1335 | 1482 |
| LMArena Chinese | — | 1533 |
| LMArena German | 1370 | — |
Instruction Following Qwen3.7 Max leads
Gemma 3 12B: 68.8 (#179), Qwen3.7 Max: 76.9 (#34)
| Benchmark | Gemma 3 12B | Qwen3.7 Max |
|---|---|---|
| LMArena Instruction Following | 1299 | 1460 |
Long Context Qwen3.7 Max leads
Gemma 3 12B: 40.0 (#157), Qwen3.7 Max: 45.4 (#34)
| Benchmark | Gemma 3 12B | Qwen3.7 Max |
|---|---|---|
| LMArena Longer Query | 1317 | 1484 |
Writing & Preference Qwen3.7 Max leads
Gemma 3 12B: 47.7 (#205), Qwen3.7 Max: 65.2 (#52)
| Benchmark | Gemma 3 12B | Qwen3.7 Max |
|---|---|---|
| LMArena Text | 1334 | 1476 |
| LMArena Creative Writing | 1331 | 1450 |
| LMArena Multi-Turn | 1334 | 1482 |
| EQ-Bench Creative Writing | 1126 | — |
| EQ-Bench 4 | — | 1110 |
Frequently asked questions
Is Gemma 3 12B better than Qwen3.7 Max?
Qwen3.7 Max is the stronger model overall, scoring 51.4 to 31.8 on the Noometry Index. Gemma 3 12B costs 50× less per token, which makes it the better buy when Qwen3.7 Max's lead doesn't matter for your workload.
Which is cheaper, Gemma 3 12B or Qwen3.7 Max?
Gemma 3 12B is cheaper. It lists at $0.05 per million input tokens and $0.15 per million output tokens; Qwen3.7 Max lists at $2.50 and $7.50.
Is Gemma 3 12B or Qwen3.7 Max better for coding?
Qwen3.7 Max scores higher on coding benchmarks: 50.2 versus 31.2 in the Noometry coding category.
Which has the bigger context window?
Qwen3.7 Max does, with 1M tokens against 131K.
How many benchmarks do Gemma 3 12B and Qwen3.7 Max share?
19 benchmarks have published results for both models. Gemma 3 12B has 24 scored results on Noometry and Qwen3.7 Max has 33.