Model comparison
Gemma 2B vs Qwen1.5 4b Chat
Gemma 2B and Qwen1.5 4b Chat score almost the same on the Noometry Index (29.1 vs 28.3), so choose on price, context window or the category you care about most.
Last verified . 11 shared benchmarks.
Google
Alibaba (Qwen)Summary
- They share 11 benchmarks with published results for both. Gemma 2B scores higher in 3 categories and Qwen1.5 4b Chat in 4 categories; one gap is clear of the uncertainty.
Side by side
| Gemma 2B | Qwen1.5 4b Chat | |
|---|---|---|
| Provider | Alibaba (Qwen) | |
| Noometry Index | 29.1 | 28.3 |
| Released | 2024-02-21 | — |
| Weights | Open | Open |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 23 | 13 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Too close to call
Gemma 2B: 28.9 (#300), Qwen1.5 4b Chat: 28.6 (#305)
| Benchmark | Gemma 2B | Qwen1.5 4b Chat |
|---|---|---|
| LMArena Coding | 1010 | 999 |
| HumanEval+ | 20.7% | — |
| MBPP+ | 34.1% | — |
Reasoning Too close to call
Gemma 2B: 17.9 (#275), Qwen1.5 4b Chat: 17.7 (#277)
| Benchmark | Gemma 2B | Qwen1.5 4b Chat |
|---|---|---|
| LMArena Hard Prompts | 989 | 976 |
| BIG-Bench Hard | 35.2% | — |
| Epoch Capabilities Index | 93.57 | — |
| HellaSwag | 71.4% | — |
| PIQA | 77.3% | — |
| WinoGrande | 65.4% | — |
Math Too close to call
Gemma 2B: 27.6 (#237), Qwen1.5 4b Chat: 27.9 (#233)
| Benchmark | Gemma 2B | Qwen1.5 4b Chat |
|---|---|---|
| LMArena Math | 1009 | 1026 |
| GSM8K | 17.7% | — |
Knowledge Not comparable
Gemma 2B: —, Qwen1.5 4b Chat: 26.2 (#252)
| Benchmark | Gemma 2B | Qwen1.5 4b Chat |
|---|---|---|
| LMArena Expert | — | 980 |
| ARC (AI2) Challenge | 42.1% | — |
| BoolQ | 69.4% | — |
| MMLU | 42.3% | — |
| TriviaQA | 53.2% | — |
Multilingual Qwen1.5 4b Chat leads
Gemma 2B: 23.1 (#289), Qwen1.5 4b Chat: 24.2 (#285)
| Benchmark | Gemma 2B | Qwen1.5 4b Chat |
|---|---|---|
| LMArena Non-English | 958 | 979 |
| LMArena Chinese | 986 | 1024 |
| LMArena Russian | 937 | 952 |
| LMArena German | — | 902 |
Instruction Following Too close to call
Gemma 2B: 48.8 (#297), Qwen1.5 4b Chat: 49.3 (#295)
| Benchmark | Gemma 2B | Qwen1.5 4b Chat |
|---|---|---|
| LMArena Instruction Following | 971 | 979 |
Long Context Too close to call
Gemma 2B: 29.9 (#286), Qwen1.5 4b Chat: 30.1 (#285)
| Benchmark | Gemma 2B | Qwen1.5 4b Chat |
|---|---|---|
| LMArena Longer Query | 981 | 988 |
Writing & Preference Too close to call
Gemma 2B: 24.1 (#303), Qwen1.5 4b Chat: 23.9 (#304)
| Benchmark | Gemma 2B | Qwen1.5 4b Chat |
|---|---|---|
| LMArena Text | 1002 | 997 |
| LMArena Creative Writing | 986 | 969 |
| LMArena Multi-Turn | 945 | 977 |
Frequently asked questions
Is Gemma 2B better than Qwen1.5 4b Chat?
Gemma 2B and Qwen1.5 4b Chat score almost the same on the Noometry Index (29.1 vs 28.3), so choose on price, context window or the category you care about most.
Is Gemma 2B or Qwen1.5 4b Chat better for coding?
They score almost the same on coding (28.9 vs 28.6); test both on your own repository before choosing.
How many benchmarks do Gemma 2B and Qwen1.5 4b Chat share?
11 benchmarks have published results for both models. Gemma 2B has 23 scored results on Noometry and Qwen1.5 4b Chat has 13.