Model comparison
Gemma 3 12B vs Qwen3.6 Plus
Qwen3.6 Plus is the stronger model overall, scoring 47.3 to 31.8 on the Noometry Index. Gemma 3 12B costs 15× less per token, which makes it the better buy when Qwen3.6 Plus's lead doesn't matter for your workload.
Last verified . 20 shared benchmarks.
Google
Alibaba (Qwen)Summary
- They share 20 benchmarks with published results for both. Gemma 3 12B scores higher in 0 categories and Qwen3.6 Plus in 8 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Qwen3.6 Plus leads 56.1 to 26.5.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 16.7% for Gemma 3 12B and 93.3% for Qwen3.6 Plus.
- Gemma 3 12B is cheaper at $0.05 / $0.15 per million input/output tokens, against $0.50 / $3 for Qwen3.6 Plus.
- Qwen3.6 Plus 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 | Qwen3.6 Plus | |
|---|---|---|
| Provider | Alibaba (Qwen) | |
| Noometry Index | 31.8 | 47.3 |
| Released | 2025-03-12 | 2026-03-31 |
| Weights | Open | Proprietary |
| Context window | 131K | 1M |
| Max output | 8K | 66K |
| Input $ / M tokens | $0.05 | $0.50 |
| Output $ / M tokens | $0.15 | $3 |
| Results tracked | 24 | 37 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Qwen3.6 Plus leads
Gemma 3 12B: 31.2 (#276), Qwen3.6 Plus: 40.6 (#125)
| Benchmark | Gemma 3 12B | Qwen3.6 Plus |
|---|---|---|
| SciCode | 17.4% | 40.7% |
| LMArena Coding | 1281 | 1467 |
| SWE-bench Verified | — | 57.9% |
| LMArena WebDev | — | 1461 |
| ALE-Bench | — | 670.15 |
Agentic & Tool Use Not comparable
Gemma 3 12B: 25.3 (#101), Qwen3.6 Plus: —
| Benchmark | Gemma 3 12B | Qwen3.6 Plus |
|---|---|---|
| Berkeley Function Calling Leaderboard | 30.4% | — |
| Vending-Bench 2 | — | 5,115 |
Reasoning Qwen3.6 Plus leads
Gemma 3 12B: 15.2 (#307), Qwen3.6 Plus: 28.5 (#89)
| Benchmark | Gemma 3 12B | Qwen3.6 Plus |
|---|---|---|
| CritPt | 0% | 2.9% |
| Chess Puzzles | 0% | 17% |
| LMArena Hard Prompts | 1309 | 1449 |
| DTBench | 48.8% | 81.9% |
| LMCA | 4.5% | 33.1% |
| Epoch Capabilities Index | 123.49 | 147.67 |
| NYT Connections (extended) | — | 60.3% |
| Thematic Generalization | — | 59.5% |
| Mystery Game Puzzles | — | 12% |
Math Qwen3.6 Plus leads
Gemma 3 12B: 21.0 (#273), Qwen3.6 Plus: 50.6 (#44)
| Benchmark | Gemma 3 12B | Qwen3.6 Plus |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 16.7% | 93.3% |
| LMArena Math | 1307 | 1450 |
| FrontierMath (Tiers 1-3) | — | 38.2% |
| FrontierMath (Feb 2025 set) | — | 26.2% |
| FrontierMath Tier 4 (v1) | — | 8.3% |
Knowledge Qwen3.6 Plus leads
Gemma 3 12B: 26.5 (#250), Qwen3.6 Plus: 56.1 (#40)
| Benchmark | Gemma 3 12B | Qwen3.6 Plus |
|---|---|---|
| GPQA Diamond | 39.5% | 88.4% |
| LMArena Expert | 1248 | 1456 |
| SimpleQA Verified | — | 44.1% |
| Vectara Hallucination Rate | 4.4% | — |
Multimodal Not comparable
Gemma 3 12B: —, Qwen3.6 Plus: —
| Benchmark | Gemma 3 12B | Qwen3.6 Plus |
|---|---|---|
| MindCube | 46.7% | — |
Multilingual Qwen3.6 Plus leads
Gemma 3 12B: 45.9 (#160), Qwen3.6 Plus: 53.5 (#66)
| Benchmark | Gemma 3 12B | Qwen3.6 Plus |
|---|---|---|
| LMArena Non-English | 1318 | 1424 |
| LMArena German | 1370 | 1451 |
| LMArena Russian | 1335 | 1434 |
| LMArena Chinese | — | 1478 |
| LMArena French | — | 1454 |
| LMArena Japanese | — | 1389 |
| LMArena Korean | — | 1381 |
| LMArena Spanish | — | 1432 |
Instruction Following Qwen3.6 Plus leads
Gemma 3 12B: 68.8 (#179), Qwen3.6 Plus: 75.2 (#70)
| Benchmark | Gemma 3 12B | Qwen3.6 Plus |
|---|---|---|
| LMArena Instruction Following | 1299 | 1425 |
Long Context Qwen3.6 Plus leads
Gemma 3 12B: 40.0 (#157), Qwen3.6 Plus: 45.1 (#48)
| Benchmark | Gemma 3 12B | Qwen3.6 Plus |
|---|---|---|
| LMArena Longer Query | 1317 | 1440 |
| CL-bench | — | 20.3% |
Writing & Preference Qwen3.6 Plus leads
Gemma 3 12B: 47.7 (#205), Qwen3.6 Plus: 62.4 (#78)
| Benchmark | Gemma 3 12B | Qwen3.6 Plus |
|---|---|---|
| LMArena Text | 1334 | 1437 |
| LMArena Creative Writing | 1331 | 1405 |
| LMArena Multi-Turn | 1334 | 1438 |
| EQ-Bench Creative Writing | 1126 | — |
Frequently asked questions
Is Gemma 3 12B better than Qwen3.6 Plus?
Qwen3.6 Plus is the stronger model overall, scoring 47.3 to 31.8 on the Noometry Index. Gemma 3 12B costs 15× less per token, which makes it the better buy when Qwen3.6 Plus's lead doesn't matter for your workload.
Which is cheaper, Gemma 3 12B or Qwen3.6 Plus?
Gemma 3 12B is cheaper. It lists at $0.05 per million input tokens and $0.15 per million output tokens; Qwen3.6 Plus lists at $0.50 and $3.
Is Gemma 3 12B or Qwen3.6 Plus better for coding?
Qwen3.6 Plus scores higher on coding benchmarks: 40.6 versus 31.2 in the Noometry coding category.
Which has the bigger context window?
Qwen3.6 Plus does, with 1M tokens against 131K.
How many benchmarks do Gemma 3 12B and Qwen3.6 Plus share?
20 benchmarks have published results for both models. Gemma 3 12B has 24 scored results on Noometry and Qwen3.6 Plus has 37.