Model comparison
Gemma 2B vs Qwen3 32B
Qwen3 32B is the stronger model overall, scoring 39.2 to 29.6 on the Noometry Index.
Last verified . 12 shared benchmarks.
Google
Alibaba (Qwen)Summary
- They share 12 benchmarks with published results for both. Gemma 2B scores higher in 0 categories and Qwen3 32B in 7 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Qwen3 32B leads 52.9 to 24.0.
Side by side
| Gemma 2B | Qwen3 32B | |
|---|---|---|
| Provider | Alibaba (Qwen) | |
| Noometry Index | 29.6 | 39.2 |
| Released | 2024-02-21 | 2025-04 |
| Weights | Open | Open |
| Context window | — | 131K |
| Max output | — | 16K |
| Input $ / M tokens | — | $0.70 |
| Output $ / M tokens | — | $2.80 |
| Results tracked | 23 | 26 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Qwen3 32B leads
Gemma 2B: 29.4 (#305), Qwen3 32B: 37.7 (#190)
| Benchmark | Gemma 2B | Qwen3 32B |
|---|---|---|
| LMArena Coding | 1010 | 1358 |
| Aider Polyglot | — | 40% |
| SciCode | — | 35.4% |
| HumanEval+ | 20.7% | — |
| MBPP+ | 34.1% | — |
Agentic & Tool Use Not comparable
Gemma 2B: —, Qwen3 32B: 32.6 (#62)
| Benchmark | Gemma 2B | Qwen3 32B |
|---|---|---|
| Berkeley Function Calling Leaderboard | — | 48.7% |
Reasoning Qwen3 32B leads
Gemma 2B: 18.8 (#275), Qwen3 32B: 20.2 (#241)
| Benchmark | Gemma 2B | Qwen3 32B |
|---|---|---|
| LMArena Hard Prompts | 989 | 1334 |
| Epoch Capabilities Index | 94.2 | 138.51 |
| Kagi LLM Benchmark | — | 54.9% |
| CritPt | — | 0.3% |
| Chess Puzzles | — | 5% |
| DTBench | — | 67.5% |
| LMCA | — | 17.3% |
| BIG-Bench Hard | 35.2% | — |
| HellaSwag | 71.4% | — |
| PIQA | 77.3% | — |
| WinoGrande | 65.4% | — |
Math Qwen3 32B leads
Gemma 2B: 30.0 (#239), Qwen3 32B: 39.7 (#99)
| Benchmark | Gemma 2B | Qwen3 32B |
|---|---|---|
| LMArena Math | 1009 | 1399 |
| OTIS Mock AIME 2024-2025 | — | 66.9% |
| GSM8K | 17.7% | — |
Knowledge Not comparable
Gemma 2B: —, Qwen3 32B: 40.0 (#125)
| Benchmark | Gemma 2B | Qwen3 32B |
|---|---|---|
| GPQA Diamond | — | 65.7% |
| Vectara Hallucination Rate | — | 5.9% |
| LMArena Expert | — | 1362 |
| ARC (AI2) Challenge | 42.1% | — |
| BoolQ | 69.4% | — |
| MMLU | 42.3% | — |
| TriviaQA | 53.2% | — |
Multilingual Qwen3 32B leads
Gemma 2B: 23.0 (#294), Qwen3 32B: 45.6 (#167)
| Benchmark | Gemma 2B | Qwen3 32B |
|---|---|---|
| LMArena Non-English | 958 | 1317 |
| LMArena Chinese | 986 | 1357 |
| LMArena Russian | 937 | 1311 |
| LMArena German | — | 1341 |
Instruction Following Qwen3 32B leads
Gemma 2B: 48.5 (#302), Qwen3 32B: 68.9 (#179)
| Benchmark | Gemma 2B | Qwen3 32B |
|---|---|---|
| LMArena Instruction Following | 970 | 1305 |
Long Context Qwen3 32B leads
Gemma 2B: 29.9 (#291), Qwen3 32B: 43.8 (#87)
| Benchmark | Gemma 2B | Qwen3 32B |
|---|---|---|
| LMArena Longer Query | 981 | 1327 |
| Fiction.LiveBench | — | 74.2% |
Writing & Preference Qwen3 32B leads
Gemma 2B: 24.0 (#308), Qwen3 32B: 52.9 (#163)
| Benchmark | Gemma 2B | Qwen3 32B |
|---|---|---|
| LMArena Text | 1002 | 1340 |
| LMArena Creative Writing | 987 | 1297 |
| LMArena Multi-Turn | 945 | 1331 |
Frequently asked questions
Is Gemma 2B better than Qwen3 32B?
Qwen3 32B is the stronger model overall, scoring 39.2 to 29.6 on the Noometry Index.
Is Gemma 2B or Qwen3 32B better for coding?
Qwen3 32B scores higher on coding benchmarks: 37.7 versus 29.4 in the Noometry coding category.
How many benchmarks do Gemma 2B and Qwen3 32B share?
12 benchmarks have published results for both models. Gemma 2B has 23 scored results on Noometry and Qwen3 32B has 26.