Model comparison
Gemma 3 12B vs Qwen1.5 4b Chat
Gemma 3 12B is the stronger model overall, scoring 32.1 to 28.8 on the Noometry Index.
Last verified . 12 shared benchmarks.
Google
Alibaba (Qwen)Summary
- They share 12 benchmarks with published results for both. Gemma 3 12B scores higher in 5 categories and Qwen1.5 4b Chat in 3 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Gemma 3 12B leads 47.5 to 23.8.
Side by side
| Gemma 3 12B | Qwen1.5 4b Chat | |
|---|---|---|
| Provider | Alibaba (Qwen) | |
| Noometry Index | 32.1 | 28.8 |
| Released | 2025-03-12 | — |
| Weights | Open | Open |
| Context window | 131K | — |
| Max output | 8K | — |
| Input $ / M tokens | $0.05 | — |
| Output $ / M tokens | $0.15 | — |
| Results tracked | 24 | 13 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Gemma 3 12B leads
Gemma 3 12B: 31.7 (#280), Qwen1.5 4b Chat: 29.1 (#308)
| Benchmark | Gemma 3 12B | Qwen1.5 4b Chat |
|---|---|---|
| LMArena Coding | 1281 | 999 |
| SciCode | 17.4% | — |
Agentic & Tool Use Not comparable
Gemma 3 12B: 25.5 (#108), Qwen1.5 4b Chat: —
| Benchmark | Gemma 3 12B | Qwen1.5 4b Chat |
|---|---|---|
| Berkeley Function Calling Leaderboard | 30.4% | — |
Reasoning Qwen1.5 4b Chat leads
Gemma 3 12B: 15.7 (#313), Qwen1.5 4b Chat: 18.5 (#279)
| Benchmark | Gemma 3 12B | Qwen1.5 4b Chat |
|---|---|---|
| LMArena Hard Prompts | 1309 | 976 |
| CritPt | 0% | — |
| Chess Puzzles | 0% | — |
| DTBench | 48.8% | — |
| LMCA | 4.5% | — |
| Epoch Capabilities Index | 123.5 | — |
Math Qwen1.5 4b Chat leads
Gemma 3 12B: 22.3 (#279), Qwen1.5 4b Chat: 30.4 (#234)
| Benchmark | Gemma 3 12B | Qwen1.5 4b Chat |
|---|---|---|
| LMArena Math | 1307 | 1026 |
| OTIS Mock AIME 2024-2025 | 16.7% | — |
Knowledge Too close to call
Gemma 3 12B: 26.5 (#257), Qwen1.5 4b Chat: 26.7 (#255)
| Benchmark | Gemma 3 12B | Qwen1.5 4b Chat |
|---|---|---|
| LMArena Expert | 1248 | 980 |
| GPQA Diamond | 39.5% | — |
| Vectara Hallucination Rate | 4.4% | — |
Multimodal Not comparable
Gemma 3 12B: —, Qwen1.5 4b Chat: —
| Benchmark | Gemma 3 12B | Qwen1.5 4b Chat |
|---|---|---|
| MindCube | 46.7% | — |
Multilingual Gemma 3 12B leads
Gemma 3 12B: 45.7 (#165), Qwen1.5 4b Chat: 24.1 (#290)
| Benchmark | Gemma 3 12B | Qwen1.5 4b Chat |
|---|---|---|
| LMArena Non-English | 1318 | 979 |
| LMArena German | 1370 | 902 |
| LMArena Russian | 1335 | 952 |
| LMArena Chinese | — | 1024 |
Instruction Following Gemma 3 12B leads
Gemma 3 12B: 68.6 (#186), Qwen1.5 4b Chat: 49.0 (#300)
| Benchmark | Gemma 3 12B | Qwen1.5 4b Chat |
|---|---|---|
| LMArena Instruction Following | 1299 | 978 |
Long Context Gemma 3 12B leads
Gemma 3 12B: 40.0 (#162), Qwen1.5 4b Chat: 30.1 (#290)
| Benchmark | Gemma 3 12B | Qwen1.5 4b Chat |
|---|---|---|
| LMArena Longer Query | 1317 | 988 |
Writing & Preference Gemma 3 12B leads
Gemma 3 12B: 47.5 (#209), Qwen1.5 4b Chat: 23.8 (#309)
| Benchmark | Gemma 3 12B | Qwen1.5 4b Chat |
|---|---|---|
| LMArena Text | 1334 | 997 |
| LMArena Creative Writing | 1331 | 969 |
| LMArena Multi-Turn | 1334 | 977 |
| EQ-Bench Creative Writing | 1126 | — |
Frequently asked questions
Is Gemma 3 12B better than Qwen1.5 4b Chat?
Gemma 3 12B is the stronger model overall, scoring 32.1 to 28.8 on the Noometry Index.
Is Gemma 3 12B or Qwen1.5 4b Chat better for coding?
Gemma 3 12B scores higher on coding benchmarks: 31.7 versus 29.1 in the Noometry coding category.
How many benchmarks do Gemma 3 12B and Qwen1.5 4b Chat share?
12 benchmarks have published results for both models. Gemma 3 12B has 24 scored results on Noometry and Qwen1.5 4b Chat has 13.