Model comparison
Gemma 3 12B vs Qwen3.6 27B
Qwen3.6 27B is the stronger model overall, scoring 41.9 to 31.8 on the Noometry Index. Gemma 3 12B costs 18× less per token, which makes it the better buy when Qwen3.6 27B's lead doesn't matter for your workload.
Last verified . 8 shared benchmarks.
Google
Alibaba (Qwen)Summary
- They share 8 benchmarks with published results for both. Gemma 3 12B scores higher in 0 categories and Qwen3.6 27B in 5 categories; 5 gaps are clear of the uncertainty.
- The widest gap is in math, where Qwen3.6 27B leads 47.5 to 21.0.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 16.7% for Gemma 3 12B and 91.1% for Qwen3.6 27B.
- Gemma 3 12B is cheaper at $0.05 / $0.15 per million input/output tokens, against $0.60 / $3.60 for Qwen3.6 27B.
- Qwen3.6 27B accepts more context: 262K tokens versus 131K.
Side by side
| Gemma 3 12B | Qwen3.6 27B | |
|---|---|---|
| Provider | Alibaba (Qwen) | |
| Noometry Index | 31.8 | 41.9 |
| Released | 2025-03-12 | 2026-04-22 |
| Weights | Open | Open |
| Context window | 131K | 262K |
| Max output | 8K | 66K |
| Input $ / M tokens | $0.05 | $0.60 |
| Output $ / M tokens | $0.15 | $3.60 |
| Results tracked | 24 | 11 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Qwen3.6 27B leads
Gemma 3 12B: 31.2 (#276), Qwen3.6 27B: 38.5 (#162)
| Benchmark | Gemma 3 12B | Qwen3.6 27B |
|---|---|---|
| SciCode | 17.4% | 37.3% |
| LMArena Coding | 1281 | — |
Agentic & Tool Use Not comparable
Gemma 3 12B: 25.3 (#101), Qwen3.6 27B: —
| Benchmark | Gemma 3 12B | Qwen3.6 27B |
|---|---|---|
| Berkeley Function Calling Leaderboard | 30.4% | — |
Reasoning Qwen3.6 27B leads
Gemma 3 12B: 15.2 (#307), Qwen3.6 27B: 24.4 (#148)
| Benchmark | Gemma 3 12B | Qwen3.6 27B |
|---|---|---|
| CritPt | 0% | 0.9% |
| Chess Puzzles | 0% | 22% |
| DTBench | 48.8% | 78.1% |
| LMCA | 4.5% | 34.5% |
| Epoch Capabilities Index | 123.49 | 146.47 |
| LMArena Hard Prompts | 1309 | — |
| Mystery Game Puzzles | — | 7% |
Math Qwen3.6 27B leads
Gemma 3 12B: 21.0 (#273), Qwen3.6 27B: 47.5 (#56)
| Benchmark | Gemma 3 12B | Qwen3.6 27B |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 16.7% | 91.1% |
| FrontierMath (Tiers 1-3) | — | 35.1% |
| LMArena Math | 1307 | — |
Knowledge Qwen3.6 27B leads
Gemma 3 12B: 26.5 (#250), Qwen3.6 27B: 52.4 (#58)
| Benchmark | Gemma 3 12B | Qwen3.6 27B |
|---|---|---|
| GPQA Diamond | 39.5% | 85.9% |
| Vectara Hallucination Rate | 4.4% | — |
| LMArena Expert | 1248 | — |
Multimodal Not comparable
Gemma 3 12B: —, Qwen3.6 27B: —
| Benchmark | Gemma 3 12B | Qwen3.6 27B |
|---|---|---|
| MindCube | 46.7% | — |
Multilingual Not comparable
Gemma 3 12B: 45.9 (#160), Qwen3.6 27B: —
| Benchmark | Gemma 3 12B | Qwen3.6 27B |
|---|---|---|
| LMArena Non-English | 1318 | — |
| LMArena German | 1370 | — |
| LMArena Russian | 1335 | — |
Instruction Following Not comparable
Gemma 3 12B: 68.8 (#179), Qwen3.6 27B: —
| Benchmark | Gemma 3 12B | Qwen3.6 27B |
|---|---|---|
| LMArena Instruction Following | 1299 | — |
Long Context Not comparable
Gemma 3 12B: 40.0 (#157), Qwen3.6 27B: —
| Benchmark | Gemma 3 12B | Qwen3.6 27B |
|---|---|---|
| LMArena Longer Query | 1317 | — |
Writing & Preference Qwen3.6 27B leads
Gemma 3 12B: 47.7 (#205), Qwen3.6 27B: 50.3 (#180)
| Benchmark | Gemma 3 12B | Qwen3.6 27B |
|---|---|---|
| LMArena Text | 1334 | — |
| LMArena Creative Writing | 1331 | — |
| EQ-Bench Creative Writing | 1126 | — |
| EQ-Bench 4 | — | 1026 |
| LMArena Multi-Turn | 1334 | — |
Frequently asked questions
Is Gemma 3 12B better than Qwen3.6 27B?
Qwen3.6 27B is the stronger model overall, scoring 41.9 to 31.8 on the Noometry Index. Gemma 3 12B costs 18× less per token, which makes it the better buy when Qwen3.6 27B's lead doesn't matter for your workload.
Which is cheaper, Gemma 3 12B or Qwen3.6 27B?
Gemma 3 12B is cheaper. It lists at $0.05 per million input tokens and $0.15 per million output tokens; Qwen3.6 27B lists at $0.60 and $3.60.
Is Gemma 3 12B or Qwen3.6 27B better for coding?
Qwen3.6 27B scores higher on coding benchmarks: 38.5 versus 31.2 in the Noometry coding category.
Which has the bigger context window?
Qwen3.6 27B does, with 262K tokens against 131K.
How many benchmarks do Gemma 3 12B and Qwen3.6 27B share?
8 benchmarks have published results for both models. Gemma 3 12B has 24 scored results on Noometry and Qwen3.6 27B has 11.