Model comparison
Gemma 3 4B vs Qwen1.5-32B
Qwen1.5-32B is the stronger model overall, scoring 30.0 to 27.9 on the Noometry Index.
Last verified . 13 shared benchmarks.
Google
Alibaba (Qwen)Summary
- They share 13 benchmarks with published results for both. Gemma 3 4B scores higher in 5 categories and Qwen1.5-32B in 3 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in math, where Qwen1.5-32B leads 30.5 to 15.8.
- The biggest single-benchmark swing is GPQA Diamond: 23.2% for Gemma 3 4B and 30.7% for Qwen1.5-32B.
Side by side
| Gemma 3 4B | Qwen1.5-32B | |
|---|---|---|
| Provider | Alibaba (Qwen) | |
| Noometry Index | 27.9 | 30.0 |
| Released | 2025-03-12 | 2024-02-04 |
| Weights | Open | Open |
| Context window | 131K | — |
| Max output | 4K | — |
| Input $ / M tokens | $0.04 | — |
| Output $ / M tokens | $0.08 | — |
| Results tracked | 22 | 21 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Gemma 3 4B leads
Gemma 3 4B: 35.3 (#214), Qwen1.5-32B: 31.1 (#278)
| Benchmark | Gemma 3 4B | Qwen1.5-32B |
|---|---|---|
| LMArena Coding | 1230 | 1155 |
| BigCodeBench Instruct | — | 32.3% |
| BigCodeBench Complete | — | 42% |
Agentic & Tool Use Not comparable
Gemma 3 4B: 20.7 (#134), Qwen1.5-32B: —
| Benchmark | Gemma 3 4B | Qwen1.5-32B |
|---|---|---|
| Berkeley Function Calling Leaderboard | 19.6% | — |
Reasoning Qwen1.5-32B leads
Gemma 3 4B: 12.7 (#330), Qwen1.5-32B: 20.9 (#210)
| Benchmark | Gemma 3 4B | Qwen1.5-32B |
|---|---|---|
| LMArena Hard Prompts | 1253 | 1131 |
| Kagi LLM Benchmark | 25.2% | — |
| Chess Puzzles | 0% | — |
| DTBench | 50.9% | — |
| LMCA | 2.8% | — |
| Epoch Capabilities Index | 116.02 | — |
Math Qwen1.5-32B leads
Gemma 3 4B: 15.8 (#286), Qwen1.5-32B: 30.5 (#207)
| Benchmark | Gemma 3 4B | Qwen1.5-32B |
|---|---|---|
| LMArena Math | 1239 | 1155 |
| OTIS Mock AIME 2024-2025 | 7.5% | — |
Knowledge Qwen1.5-32B leads
Gemma 3 4B: 11.8 (#294), Qwen1.5-32B: 13.5 (#291)
| Benchmark | Gemma 3 4B | Qwen1.5-32B |
|---|---|---|
| GPQA Diamond | 23.2% | 30.7% |
| LMArena Expert | 1223 | 1126 |
| Vectara Hallucination Rate | 6.4% | — |
| MMLU | — | 74.4% |
Multilingual Gemma 3 4B leads
Gemma 3 4B: 42.7 (#189), Qwen1.5-32B: 31.6 (#254)
| Benchmark | Gemma 3 4B | Qwen1.5-32B |
|---|---|---|
| LMArena Non-English | 1273 | 1106 |
| LMArena German | 1281 | 1058 |
| LMArena Russian | 1294 | 1073 |
| LMArena Chinese | — | 1176 |
| LMArena French | — | 1100 |
| LMArena Japanese | — | 1027 |
| LMArena Korean | — | 1007 |
| LMArena Spanish | — | 1089 |
Instruction Following Gemma 3 4B leads
Gemma 3 4B: 65.4 (#219), Qwen1.5-32B: 58.0 (#260)
| Benchmark | Gemma 3 4B | Qwen1.5-32B |
|---|---|---|
| LMArena Instruction Following | 1239 | 1116 |
Long Context Gemma 3 4B leads
Gemma 3 4B: 38.6 (#189), Qwen1.5-32B: 34.7 (#241)
| Benchmark | Gemma 3 4B | Qwen1.5-32B |
|---|---|---|
| LMArena Longer Query | 1274 | 1146 |
Writing & Preference Gemma 3 4B leads
Gemma 3 4B: 42.2 (#234), Qwen1.5-32B: 34.4 (#266)
| Benchmark | Gemma 3 4B | Qwen1.5-32B |
|---|---|---|
| LMArena Text | 1291 | 1137 |
| LMArena Creative Writing | 1270 | 1083 |
| LMArena Multi-Turn | 1255 | 1140 |
| EQ-Bench Creative Writing | 1068 | — |
Frequently asked questions
Is Gemma 3 4B better than Qwen1.5-32B?
Qwen1.5-32B is the stronger model overall, scoring 30.0 to 27.9 on the Noometry Index.
Is Gemma 3 4B or Qwen1.5-32B better for coding?
Gemma 3 4B scores higher on coding benchmarks: 35.3 versus 31.1 in the Noometry coding category.
How many benchmarks do Gemma 3 4B and Qwen1.5-32B share?
13 benchmarks have published results for both models. Gemma 3 4B has 22 scored results on Noometry and Qwen1.5-32B has 21.