Model comparison
Gemma 2 2b IT vs Qwen1.5-32B
Gemma 2 2b IT is the stronger model overall, scoring 32.5 to 30.0 on the Noometry Index.
Last verified . 17 shared benchmarks.
Google
Alibaba (Qwen)Summary
- They share 17 benchmarks with published results for both. Gemma 2 2b IT scores higher in 5 categories and Qwen1.5-32B in 3 categories; 2 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Gemma 2 2b IT leads 29.3 to 13.5.
Side by side
| Gemma 2 2b IT | Qwen1.5-32B | |
|---|---|---|
| Provider | Alibaba (Qwen) | |
| Noometry Index | 32.5 | 30.0 |
| Released | — | 2024-02-04 |
| Weights | Open | Open |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 17 | 21 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Too close to call
Gemma 2 2b IT: 31.8 (#268), Qwen1.5-32B: 31.1 (#278)
| Benchmark | Gemma 2 2b IT | Qwen1.5-32B |
|---|---|---|
| LMArena Coding | 1112 | 1155 |
| BigCodeBench Instruct | — | 32.3% |
| BigCodeBench Complete | — | 42% |
Reasoning Too close to call
Gemma 2 2b IT: 20.5 (#219), Qwen1.5-32B: 20.9 (#210)
| Benchmark | Gemma 2 2b IT | Qwen1.5-32B |
|---|---|---|
| LMArena Hard Prompts | 1113 | 1131 |
Math Too close to call
Gemma 2 2b IT: 30.1 (#212), Qwen1.5-32B: 30.5 (#207)
| Benchmark | Gemma 2 2b IT | Qwen1.5-32B |
|---|---|---|
| LMArena Math | 1135 | 1155 |
Knowledge Gemma 2 2b IT leads
Gemma 2 2b IT: 29.3 (#229), Qwen1.5-32B: 13.5 (#291)
| Benchmark | Gemma 2 2b IT | Qwen1.5-32B |
|---|---|---|
| LMArena Expert | 1096 | 1126 |
| GPQA Diamond | — | 30.7% |
| MMLU | — | 74.4% |
Multilingual Too close to call
Gemma 2 2b IT: 32.5 (#252), Qwen1.5-32B: 31.6 (#254)
| Benchmark | Gemma 2 2b IT | Qwen1.5-32B |
|---|---|---|
| LMArena Non-English | 1121 | 1106 |
| LMArena Chinese | 1132 | 1176 |
| LMArena French | 1156 | 1100 |
| LMArena German | 1114 | 1058 |
| LMArena Japanese | 1083 | 1027 |
| LMArena Korean | 1055 | 1007 |
| LMArena Russian | 1118 | 1073 |
| LMArena Spanish | 1140 | 1089 |
Instruction Following Too close to call
Gemma 2 2b IT: 58.1 (#258), Qwen1.5-32B: 58.0 (#260)
| Benchmark | Gemma 2 2b IT | Qwen1.5-32B |
|---|---|---|
| LMArena Instruction Following | 1118 | 1116 |
Long Context Too close to call
Gemma 2 2b IT: 34.2 (#245), Qwen1.5-32B: 34.7 (#241)
| Benchmark | Gemma 2 2b IT | Qwen1.5-32B |
|---|---|---|
| LMArena Longer Query | 1130 | 1146 |
Writing & Preference Gemma 2 2b IT leads
Gemma 2 2b IT: 36.6 (#258), Qwen1.5-32B: 34.4 (#266)
| Benchmark | Gemma 2 2b IT | Qwen1.5-32B |
|---|---|---|
| LMArena Text | 1156 | 1137 |
| LMArena Creative Writing | 1147 | 1083 |
| LMArena Multi-Turn | 1118 | 1140 |
Frequently asked questions
Is Gemma 2 2b IT better than Qwen1.5-32B?
Gemma 2 2b IT is the stronger model overall, scoring 32.5 to 30.0 on the Noometry Index.
Is Gemma 2 2b IT or Qwen1.5-32B better for coding?
They score almost the same on coding (31.8 vs 31.1); test both on your own repository before choosing.
How many benchmarks do Gemma 2 2b IT and Qwen1.5-32B share?
17 benchmarks have published results for both models. Gemma 2 2b IT has 17 scored results on Noometry and Qwen1.5-32B has 21.