Model comparison
Gemma 2 9B vs Qwen1.5-32B
Qwen1.5-32B is the stronger model overall, scoring 30.5 to 25.9 on the Noometry Index.
Last verified . 21 shared benchmarks.
Google
Alibaba (Qwen)Summary
- They share 21 benchmarks with published results for both. Gemma 2 9B scores higher in 2 categories and Qwen1.5-32B in 6 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in math, where Qwen1.5-32B leads 33.0 to 9.9.
Side by side
| Gemma 2 9B | Qwen1.5-32B | |
|---|---|---|
| Provider | Alibaba (Qwen) | |
| Noometry Index | 25.9 | 30.5 |
| Released | 2024-06-24 | 2024-02-04 |
| Weights | Open | Open |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 35 | 21 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Qwen1.5-32B leads
Gemma 2 9B: 29.4 (#304), Qwen1.5-32B: 31.7 (#282)
| Benchmark | Gemma 2 9B | Qwen1.5-32B |
|---|---|---|
| BigCodeBench Instruct | 34.7% | 32.3% |
| LMArena Coding | 1173 | 1155 |
| BigCodeBench Complete | 40.6% | 42% |
| LiveBench Coding | 22.5% | — |
Reasoning Qwen1.5-32B leads
Gemma 2 9B: 15.9 (#309), Qwen1.5-32B: 21.8 (#212)
| Benchmark | Gemma 2 9B | Qwen1.5-32B |
|---|---|---|
| LMArena Hard Prompts | 1171 | 1130 |
| LiveBench Reasoning | 15.2% | — |
| LiveBench Data Analysis | 36.4% | — |
| Epoch Capabilities Index | 119.83 | — |
| LiveBench | 28.7% | — |
| PIQA | 83.7% | — |
Math Qwen1.5-32B leads
Gemma 2 9B: 9.9 (#318), Qwen1.5-32B: 33.0 (#207)
| Benchmark | Gemma 2 9B | Qwen1.5-32B |
|---|---|---|
| LMArena Math | 1183 | 1155 |
| OTIS Mock AIME 2024-2025 | 0.6% | — |
| LiveBench Math | 19.8% | — |
| MATH Level 5 | 21% | — |
| GSM8K | 84.9% | — |
Knowledge Qwen1.5-32B leads
Gemma 2 9B: 9.7 (#305), Qwen1.5-32B: 13.5 (#296)
| Benchmark | Gemma 2 9B | Qwen1.5-32B |
|---|---|---|
| GPQA Diamond | 27.5% | 30.7% |
| LMArena Expert | 1147 | 1126 |
| MMLU | 72.1% | 74.4% |
| BoolQ | 85.7% | — |
Multilingual Gemma 2 9B leads
Gemma 2 9B: 36.6 (#238), Qwen1.5-32B: 31.4 (#259)
| Benchmark | Gemma 2 9B | Qwen1.5-32B |
|---|---|---|
| LMArena Non-English | 1188 | 1106 |
| LMArena Chinese | 1185 | 1177 |
| LMArena French | 1190 | 1101 |
| LMArena German | 1186 | 1058 |
| LMArena Japanese | 1144 | 1027 |
| LMArena Korean | 1137 | 1008 |
| LMArena Russian | 1200 | 1073 |
| LMArena Spanish | 1200 | 1089 |
Instruction Following Too close to call
Gemma 2 9B: 57.6 (#269), Qwen1.5-32B: 57.7 (#265)
| Benchmark | Gemma 2 9B | Qwen1.5-32B |
|---|---|---|
| LMArena Instruction Following | 1178 | 1116 |
| LiveBench Instruction Following | 52.6% | — |
Long Context Gemma 2 9B leads
Gemma 2 9B: 36.3 (#233), Qwen1.5-32B: 34.7 (#246)
| Benchmark | Gemma 2 9B | Qwen1.5-32B |
|---|---|---|
| LMArena Longer Query | 1197 | 1146 |
Writing & Preference Qwen1.5-32B leads
Gemma 2 9B: 32.1 (#281), Qwen1.5-32B: 34.2 (#271)
| Benchmark | Gemma 2 9B | Qwen1.5-32B |
|---|---|---|
| LMArena Text | 1207 | 1137 |
| LMArena Creative Writing | 1206 | 1083 |
| LMArena Multi-Turn | 1193 | 1140 |
| EQ-Bench Creative Writing | 841 | — |
| LiveBench Language | 25.5% | — |
Frequently asked questions
Is Gemma 2 9B better than Qwen1.5-32B?
Qwen1.5-32B is the stronger model overall, scoring 30.5 to 25.9 on the Noometry Index.
Is Gemma 2 9B or Qwen1.5-32B better for coding?
Qwen1.5-32B scores higher on coding benchmarks: 31.7 versus 29.4 in the Noometry coding category.
How many benchmarks do Gemma 2 9B and Qwen1.5-32B share?
21 benchmarks have published results for both models. Gemma 2 9B has 35 scored results on Noometry and Qwen1.5-32B has 21.