Model comparison
Gemma 3 12B vs Qwen1.5-32B
Gemma 3 12B is the stronger model overall, scoring 31.8 to 30.0 on the Noometry Index.
Last verified . 13 shared benchmarks.
Google
Alibaba (Qwen)Summary
- They share 13 benchmarks with published results for both. Gemma 3 12B scores higher in 6 categories and Qwen1.5-32B in 2 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in multilingual, where Gemma 3 12B leads 45.9 to 31.6.
- The biggest single-benchmark swing is GPQA Diamond: 39.5% for Gemma 3 12B and 30.7% for Qwen1.5-32B.
Side by side
| Gemma 3 12B | Qwen1.5-32B | |
|---|---|---|
| Provider | Alibaba (Qwen) | |
| Noometry Index | 31.8 | 30.0 |
| Released | 2025-03-12 | 2024-02-04 |
| Weights | Open | Open |
| Context window | 131K | — |
| Max output | 8K | — |
| Input $ / M tokens | $0.05 | — |
| Output $ / M tokens | $0.15 | — |
| Results tracked | 24 | 21 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Too close to call
Gemma 3 12B: 31.2 (#276), Qwen1.5-32B: 31.1 (#278)
| Benchmark | Gemma 3 12B | Qwen1.5-32B |
|---|---|---|
| LMArena Coding | 1281 | 1155 |
| SciCode | 17.4% | — |
| BigCodeBench Instruct | — | 32.3% |
| BigCodeBench Complete | — | 42% |
Agentic & Tool Use Not comparable
Gemma 3 12B: 25.3 (#101), Qwen1.5-32B: —
| Benchmark | Gemma 3 12B | Qwen1.5-32B |
|---|---|---|
| Berkeley Function Calling Leaderboard | 30.4% | — |
Reasoning Qwen1.5-32B leads
Gemma 3 12B: 15.2 (#307), Qwen1.5-32B: 20.9 (#210)
| Benchmark | Gemma 3 12B | Qwen1.5-32B |
|---|---|---|
| LMArena Hard Prompts | 1309 | 1131 |
| CritPt | 0% | — |
| Chess Puzzles | 0% | — |
| DTBench | 48.8% | — |
| LMCA | 4.5% | — |
| Epoch Capabilities Index | 123.49 | — |
Math Qwen1.5-32B leads
Gemma 3 12B: 21.0 (#273), Qwen1.5-32B: 30.5 (#207)
| Benchmark | Gemma 3 12B | Qwen1.5-32B |
|---|---|---|
| LMArena Math | 1307 | 1155 |
| OTIS Mock AIME 2024-2025 | 16.7% | — |
Knowledge Gemma 3 12B leads
Gemma 3 12B: 26.5 (#250), Qwen1.5-32B: 13.5 (#291)
| Benchmark | Gemma 3 12B | Qwen1.5-32B |
|---|---|---|
| GPQA Diamond | 39.5% | 30.7% |
| LMArena Expert | 1248 | 1126 |
| Vectara Hallucination Rate | 4.4% | — |
| MMLU | — | 74.4% |
Multimodal Not comparable
Gemma 3 12B: —, Qwen1.5-32B: —
| Benchmark | Gemma 3 12B | Qwen1.5-32B |
|---|---|---|
| MindCube | 46.7% | — |
Multilingual Gemma 3 12B leads
Gemma 3 12B: 45.9 (#160), Qwen1.5-32B: 31.6 (#254)
| Benchmark | Gemma 3 12B | Qwen1.5-32B |
|---|---|---|
| LMArena Non-English | 1318 | 1106 |
| LMArena German | 1370 | 1058 |
| LMArena Russian | 1335 | 1073 |
| LMArena Chinese | — | 1176 |
| LMArena French | — | 1100 |
| LMArena Japanese | — | 1027 |
| LMArena Korean | — | 1007 |
| LMArena Spanish | — | 1089 |
Instruction Following Gemma 3 12B leads
Gemma 3 12B: 68.8 (#179), Qwen1.5-32B: 58.0 (#260)
| Benchmark | Gemma 3 12B | Qwen1.5-32B |
|---|---|---|
| LMArena Instruction Following | 1299 | 1116 |
Long Context Gemma 3 12B leads
Gemma 3 12B: 40.0 (#157), Qwen1.5-32B: 34.7 (#241)
| Benchmark | Gemma 3 12B | Qwen1.5-32B |
|---|---|---|
| LMArena Longer Query | 1317 | 1146 |
Writing & Preference Gemma 3 12B leads
Gemma 3 12B: 47.7 (#205), Qwen1.5-32B: 34.4 (#266)
| Benchmark | Gemma 3 12B | Qwen1.5-32B |
|---|---|---|
| LMArena Text | 1334 | 1137 |
| LMArena Creative Writing | 1331 | 1083 |
| LMArena Multi-Turn | 1334 | 1140 |
| EQ-Bench Creative Writing | 1126 | — |
Frequently asked questions
Is Gemma 3 12B better than Qwen1.5-32B?
Gemma 3 12B is the stronger model overall, scoring 31.8 to 30.0 on the Noometry Index.
Is Gemma 3 12B or Qwen1.5-32B better for coding?
They score almost the same on coding (31.2 vs 31.1); test both on your own repository before choosing.
How many benchmarks do Gemma 3 12B and Qwen1.5-32B share?
13 benchmarks have published results for both models. Gemma 3 12B has 24 scored results on Noometry and Qwen1.5-32B has 21.