Model comparison
Gemma 2B vs Qwen1.5-32B
Gemma 2B and Qwen1.5-32B score almost the same on the Noometry Index (29.6 vs 30.5), so choose on price, context window or the category you care about most.
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 Qwen1.5-32B in 7 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Qwen1.5-32B leads 34.2 to 24.0.
Side by side
| Gemma 2B | Qwen1.5-32B | |
|---|---|---|
| Provider | Alibaba (Qwen) | |
| Noometry Index | 29.6 | 30.5 |
| Released | 2024-02-21 | 2024-02-04 |
| Weights | Open | Open |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 23 | 21 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Qwen1.5-32B leads
Gemma 2B: 29.4 (#305), Qwen1.5-32B: 31.7 (#282)
| Benchmark | Gemma 2B | Qwen1.5-32B |
|---|---|---|
| LMArena Coding | 1010 | 1155 |
| BigCodeBench Instruct | — | 32.3% |
| BigCodeBench Complete | — | 42% |
| HumanEval+ | 20.7% | — |
| MBPP+ | 34.1% | — |
Reasoning Qwen1.5-32B leads
Gemma 2B: 18.8 (#275), Qwen1.5-32B: 21.8 (#212)
| Benchmark | Gemma 2B | Qwen1.5-32B |
|---|---|---|
| LMArena Hard Prompts | 989 | 1130 |
| BIG-Bench Hard | 35.2% | — |
| Epoch Capabilities Index | 94.2 | — |
| HellaSwag | 71.4% | — |
| PIQA | 77.3% | — |
| WinoGrande | 65.4% | — |
Math Qwen1.5-32B leads
Gemma 2B: 30.0 (#239), Qwen1.5-32B: 33.0 (#207)
| Benchmark | Gemma 2B | Qwen1.5-32B |
|---|---|---|
| LMArena Math | 1009 | 1155 |
| GSM8K | 17.7% | — |
Knowledge Not comparable
Gemma 2B: —, Qwen1.5-32B: 13.5 (#296)
| Benchmark | Gemma 2B | Qwen1.5-32B |
|---|---|---|
| MMLU | 42.3% | 74.4% |
| GPQA Diamond | — | 30.7% |
| LMArena Expert | — | 1126 |
| ARC (AI2) Challenge | 42.1% | — |
| BoolQ | 69.4% | — |
| TriviaQA | 53.2% | — |
Multilingual Qwen1.5-32B leads
Gemma 2B: 23.0 (#294), Qwen1.5-32B: 31.4 (#259)
| Benchmark | Gemma 2B | Qwen1.5-32B |
|---|---|---|
| LMArena Non-English | 958 | 1106 |
| LMArena Chinese | 986 | 1177 |
| LMArena Russian | 937 | 1073 |
| LMArena French | — | 1101 |
| LMArena German | — | 1058 |
| LMArena Japanese | — | 1027 |
| LMArena Korean | — | 1008 |
| LMArena Spanish | — | 1089 |
Instruction Following Qwen1.5-32B leads
Gemma 2B: 48.5 (#302), Qwen1.5-32B: 57.7 (#265)
| Benchmark | Gemma 2B | Qwen1.5-32B |
|---|---|---|
| LMArena Instruction Following | 970 | 1116 |
Long Context Qwen1.5-32B leads
Gemma 2B: 29.9 (#291), Qwen1.5-32B: 34.7 (#246)
| Benchmark | Gemma 2B | Qwen1.5-32B |
|---|---|---|
| LMArena Longer Query | 981 | 1146 |
Writing & Preference Qwen1.5-32B leads
Gemma 2B: 24.0 (#308), Qwen1.5-32B: 34.2 (#271)
| Benchmark | Gemma 2B | Qwen1.5-32B |
|---|---|---|
| LMArena Text | 1002 | 1137 |
| LMArena Creative Writing | 987 | 1083 |
| LMArena Multi-Turn | 945 | 1140 |
Frequently asked questions
Is Gemma 2B better than Qwen1.5-32B?
Gemma 2B and Qwen1.5-32B score almost the same on the Noometry Index (29.6 vs 30.5), so choose on price, context window or the category you care about most.
Is Gemma 2B 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 2B and Qwen1.5-32B share?
12 benchmarks have published results for both models. Gemma 2B has 23 scored results on Noometry and Qwen1.5-32B has 21.