Model comparison
Gemma 2 9B vs Qwen3 32B
Qwen3 32B is the stronger model overall, scoring 39.2 to 25.9 on the Noometry Index.
Last verified . 16 shared benchmarks.
Google
Alibaba (Qwen)Summary
- They share 16 benchmarks with published results for both. Gemma 2 9B scores higher in 0 categories and Qwen3 32B in 8 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Qwen3 32B leads 40.0 to 9.7.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 0.6% for Gemma 2 9B and 66.9% for Qwen3 32B.
Side by side
| Gemma 2 9B | Qwen3 32B | |
|---|---|---|
| Provider | Alibaba (Qwen) | |
| Noometry Index | 25.9 | 39.2 |
| Released | 2024-06-24 | 2025-04 |
| Weights | Open | Open |
| Context window | — | 131K |
| Max output | — | 16K |
| Input $ / M tokens | — | $0.70 |
| Output $ / M tokens | — | $2.80 |
| Results tracked | 35 | 26 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Qwen3 32B leads
Gemma 2 9B: 29.4 (#304), Qwen3 32B: 37.7 (#190)
| Benchmark | Gemma 2 9B | Qwen3 32B |
|---|---|---|
| LMArena Coding | 1173 | 1358 |
| Aider Polyglot | — | 40% |
| SciCode | — | 35.4% |
| BigCodeBench Instruct | 34.7% | — |
| LiveBench Coding | 22.5% | — |
| BigCodeBench Complete | 40.6% | — |
Agentic & Tool Use Not comparable
Gemma 2 9B: —, Qwen3 32B: 32.6 (#62)
| Benchmark | Gemma 2 9B | Qwen3 32B |
|---|---|---|
| Berkeley Function Calling Leaderboard | — | 48.7% |
Reasoning Qwen3 32B leads
Gemma 2 9B: 15.9 (#309), Qwen3 32B: 20.2 (#241)
| Benchmark | Gemma 2 9B | Qwen3 32B |
|---|---|---|
| LMArena Hard Prompts | 1171 | 1334 |
| Epoch Capabilities Index | 119.83 | 138.51 |
| Kagi LLM Benchmark | — | 54.9% |
| CritPt | — | 0.3% |
| Chess Puzzles | — | 5% |
| LiveBench Reasoning | 15.2% | — |
| DTBench | — | 67.5% |
| LiveBench Data Analysis | 36.4% | — |
| LMCA | — | 17.3% |
| LiveBench | 28.7% | — |
| PIQA | 83.7% | — |
Math Qwen3 32B leads
Gemma 2 9B: 9.9 (#318), Qwen3 32B: 39.7 (#99)
| Benchmark | Gemma 2 9B | Qwen3 32B |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 0.6% | 66.9% |
| LMArena Math | 1183 | 1399 |
| LiveBench Math | 19.8% | — |
| MATH Level 5 | 21% | — |
| GSM8K | 84.9% | — |
Knowledge Qwen3 32B leads
Gemma 2 9B: 9.7 (#305), Qwen3 32B: 40.0 (#125)
| Benchmark | Gemma 2 9B | Qwen3 32B |
|---|---|---|
| GPQA Diamond | 27.5% | 65.7% |
| LMArena Expert | 1147 | 1362 |
| Vectara Hallucination Rate | — | 5.9% |
| BoolQ | 85.7% | — |
| MMLU | 72.1% | — |
Multilingual Qwen3 32B leads
Gemma 2 9B: 36.6 (#238), Qwen3 32B: 45.6 (#167)
| Benchmark | Gemma 2 9B | Qwen3 32B |
|---|---|---|
| LMArena Non-English | 1188 | 1317 |
| LMArena Chinese | 1185 | 1357 |
| LMArena German | 1186 | 1341 |
| LMArena Russian | 1200 | 1311 |
| LMArena French | 1190 | — |
| LMArena Japanese | 1144 | — |
| LMArena Korean | 1137 | — |
| LMArena Spanish | 1200 | — |
Instruction Following Qwen3 32B leads
Gemma 2 9B: 57.6 (#269), Qwen3 32B: 68.9 (#179)
| Benchmark | Gemma 2 9B | Qwen3 32B |
|---|---|---|
| LMArena Instruction Following | 1178 | 1305 |
| LiveBench Instruction Following | 52.6% | — |
Long Context Qwen3 32B leads
Gemma 2 9B: 36.3 (#233), Qwen3 32B: 43.8 (#87)
| Benchmark | Gemma 2 9B | Qwen3 32B |
|---|---|---|
| LMArena Longer Query | 1197 | 1327 |
| Fiction.LiveBench | — | 74.2% |
Writing & Preference Qwen3 32B leads
Gemma 2 9B: 32.1 (#281), Qwen3 32B: 52.9 (#163)
| Benchmark | Gemma 2 9B | Qwen3 32B |
|---|---|---|
| LMArena Text | 1207 | 1340 |
| LMArena Creative Writing | 1206 | 1297 |
| LMArena Multi-Turn | 1193 | 1331 |
| EQ-Bench Creative Writing | 841 | — |
| LiveBench Language | 25.5% | — |
Frequently asked questions
Is Gemma 2 9B better than Qwen3 32B?
Qwen3 32B is the stronger model overall, scoring 39.2 to 25.9 on the Noometry Index.
Is Gemma 2 9B 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 2 9B and Qwen3 32B share?
16 benchmarks have published results for both models. Gemma 2 9B has 35 scored results on Noometry and Qwen3 32B has 26.