Model comparison
Gemma 3 12B vs Qwen1.5-14B
Gemma 3 12B and Qwen1.5-14B score almost the same on the Noometry Index (31.8 vs 32.1), so choose on price, context window or the category you care about most.
Last verified . 12 shared benchmarks.
Google
Alibaba (Qwen)Summary
- They share 12 benchmarks with published results for both. Gemma 3 12B scores higher in 4 categories and Qwen1.5-14B in 4 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in multilingual, where Gemma 3 12B leads 45.9 to 30.8.
Side by side
| Gemma 3 12B | Qwen1.5-14B | |
|---|---|---|
| Provider | Alibaba (Qwen) | |
| Noometry Index | 31.8 | 32.1 |
| 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 | 17 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Qwen1.5-14B leads
Gemma 3 12B: 31.2 (#276), Qwen1.5-14B: 32.5 (#259)
| Benchmark | Gemma 3 12B | Qwen1.5-14B |
|---|---|---|
| LMArena Coding | 1281 | 1138 |
| SciCode | 17.4% | — |
Agentic & Tool Use Not comparable
Gemma 3 12B: 25.3 (#101), Qwen1.5-14B: —
| Benchmark | Gemma 3 12B | Qwen1.5-14B |
|---|---|---|
| Berkeley Function Calling Leaderboard | 30.4% | — |
Reasoning Qwen1.5-14B leads
Gemma 3 12B: 15.2 (#307), Qwen1.5-14B: 20.5 (#217)
| Benchmark | Gemma 3 12B | Qwen1.5-14B |
|---|---|---|
| LMArena Hard Prompts | 1309 | 1113 |
| CritPt | 0% | — |
| Chess Puzzles | 0% | — |
| DTBench | 48.8% | — |
| LMCA | 4.5% | — |
| Epoch Capabilities Index | 123.49 | — |
Math Qwen1.5-14B leads
Gemma 3 12B: 21.0 (#273), Qwen1.5-14B: 29.9 (#214)
| Benchmark | Gemma 3 12B | Qwen1.5-14B |
|---|---|---|
| LMArena Math | 1307 | 1125 |
| OTIS Mock AIME 2024-2025 | 16.7% | — |
Knowledge Qwen1.5-14B leads
Gemma 3 12B: 26.5 (#250), Qwen1.5-14B: 29.3 (#230)
| Benchmark | Gemma 3 12B | Qwen1.5-14B |
|---|---|---|
| LMArena Expert | 1248 | 1094 |
| GPQA Diamond | 39.5% | — |
| Vectara Hallucination Rate | 4.4% | — |
| MMLU | — | 68.6% |
Multimodal Not comparable
Gemma 3 12B: —, Qwen1.5-14B: —
| Benchmark | Gemma 3 12B | Qwen1.5-14B |
|---|---|---|
| MindCube | 46.7% | — |
Multilingual Gemma 3 12B leads
Gemma 3 12B: 45.9 (#160), Qwen1.5-14B: 30.8 (#257)
| Benchmark | Gemma 3 12B | Qwen1.5-14B |
|---|---|---|
| LMArena Non-English | 1318 | 1095 |
| LMArena German | 1370 | 1043 |
| LMArena Russian | 1335 | 1046 |
| LMArena Chinese | — | 1147 |
| LMArena French | — | 1115 |
| LMArena Japanese | — | 1019 |
| LMArena Spanish | — | 1085 |
Instruction Following Gemma 3 12B leads
Gemma 3 12B: 68.8 (#179), Qwen1.5-14B: 57.1 (#266)
| Benchmark | Gemma 3 12B | Qwen1.5-14B |
|---|---|---|
| LMArena Instruction Following | 1299 | 1102 |
Long Context Gemma 3 12B leads
Gemma 3 12B: 40.0 (#157), Qwen1.5-14B: 33.7 (#252)
| Benchmark | Gemma 3 12B | Qwen1.5-14B |
|---|---|---|
| LMArena Longer Query | 1317 | 1113 |
Writing & Preference Gemma 3 12B leads
Gemma 3 12B: 47.7 (#205), Qwen1.5-14B: 33.7 (#270)
| Benchmark | Gemma 3 12B | Qwen1.5-14B |
|---|---|---|
| LMArena Text | 1334 | 1128 |
| LMArena Creative Writing | 1331 | 1091 |
| LMArena Multi-Turn | 1334 | 1110 |
| EQ-Bench Creative Writing | 1126 | — |
Frequently asked questions
Is Gemma 3 12B better than Qwen1.5-14B?
Gemma 3 12B and Qwen1.5-14B score almost the same on the Noometry Index (31.8 vs 32.1), so choose on price, context window or the category you care about most.
Is Gemma 3 12B or Qwen1.5-14B better for coding?
Qwen1.5-14B scores higher on coding benchmarks: 32.5 versus 31.2 in the Noometry coding category.
How many benchmarks do Gemma 3 12B and Qwen1.5-14B share?
12 benchmarks have published results for both models. Gemma 3 12B has 24 scored results on Noometry and Qwen1.5-14B has 17.