Model comparison
Gemma 2B vs Qwen2-72B
Gemma 2B and Qwen2-72B score almost the same on the Noometry Index (29.6 vs 30.0), so choose on price, context window or the category you care about most.
Last verified . 13 shared benchmarks.
Google
Alibaba (Qwen)Summary
- They share 13 benchmarks with published results for both. Gemma 2B scores higher in 1 category and Qwen2-72B in 6 categories; 5 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Qwen2-72B leads 40.8 to 24.0.
Side by side
| Gemma 2B | Qwen2-72B | |
|---|---|---|
| Provider | Alibaba (Qwen) | |
| Noometry Index | 29.6 | 30.0 |
| Released | 2024-02-21 | 2024-06-07 |
| Weights | Open | Open |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 23 | 26 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Too close to call
Gemma 2B: 29.4 (#305), Qwen2-72B: 29.1 (#310)
| Benchmark | Gemma 2B | Qwen2-72B |
|---|---|---|
| LMArena Coding | 1010 | 1196 |
| WeirdML | — | 11.3% |
| BigCodeBench Instruct | — | 38.5% |
| BigCodeBench Complete | — | 54% |
| HumanEval+ | 20.7% | — |
| MBPP+ | 34.1% | — |
Agentic & Tool Use Not comparable
Gemma 2B: —, Qwen2-72B: 17.0 (#146)
| Benchmark | Gemma 2B | Qwen2-72B |
|---|---|---|
| TheAgentCompany | — | 1.1% |
| METR Time Horizons | — | 29.9% |
Reasoning Qwen2-72B leads
Gemma 2B: 18.8 (#275), Qwen2-72B: 23.2 (#181)
| Benchmark | Gemma 2B | Qwen2-72B |
|---|---|---|
| LMArena Hard Prompts | 989 | 1191 |
| Epoch Capabilities Index | 94.2 | 125.28 |
| BIG-Bench Hard | 35.2% | — |
| HellaSwag | 71.4% | — |
| PIQA | 77.3% | — |
| WinoGrande | 65.4% | — |
Math Too close to call
Gemma 2B: 30.0 (#239), Qwen2-72B: 30.2 (#236)
| Benchmark | Gemma 2B | Qwen2-72B |
|---|---|---|
| LMArena Math | 1009 | 1235 |
| MATH Level 5 | — | 39.1% |
| GSM8K | 17.7% | — |
Knowledge Not comparable
Gemma 2B: —, Qwen2-72B: 21.2 (#275)
| Benchmark | Gemma 2B | Qwen2-72B |
|---|---|---|
| MMLU | 42.3% | 82.4% |
| GPQA Diamond | — | 40.8% |
| LMArena Expert | — | 1171 |
| ARC (AI2) Challenge | 42.1% | — |
| BoolQ | 69.4% | — |
| TriviaQA | 53.2% | — |
Multilingual Qwen2-72B leads
Gemma 2B: 23.0 (#294), Qwen2-72B: 35.9 (#244)
| Benchmark | Gemma 2B | Qwen2-72B |
|---|---|---|
| LMArena Non-English | 958 | 1176 |
| LMArena Chinese | 986 | 1240 |
| LMArena Russian | 937 | 1169 |
| LMArena French | — | 1170 |
| LMArena German | — | 1151 |
| LMArena Japanese | — | 1111 |
| LMArena Korean | — | 1083 |
| LMArena Spanish | — | 1169 |
Instruction Following Qwen2-72B leads
Gemma 2B: 48.5 (#302), Qwen2-72B: 61.7 (#241)
| Benchmark | Gemma 2B | Qwen2-72B |
|---|---|---|
| LMArena Instruction Following | 970 | 1181 |
Long Context Qwen2-72B leads
Gemma 2B: 29.9 (#291), Qwen2-72B: 36.1 (#235)
| Benchmark | Gemma 2B | Qwen2-72B |
|---|---|---|
| LMArena Longer Query | 981 | 1192 |
Writing & Preference Qwen2-72B leads
Gemma 2B: 24.0 (#308), Qwen2-72B: 40.8 (#241)
| Benchmark | Gemma 2B | Qwen2-72B |
|---|---|---|
| LMArena Text | 1002 | 1203 |
| LMArena Creative Writing | 987 | 1181 |
| LMArena Multi-Turn | 945 | 1196 |
Frequently asked questions
Is Gemma 2B better than Qwen2-72B?
Gemma 2B and Qwen2-72B score almost the same on the Noometry Index (29.6 vs 30.0), so choose on price, context window or the category you care about most.
Is Gemma 2B or Qwen2-72B better for coding?
They score almost the same on coding (29.4 vs 29.1); test both on your own repository before choosing.
How many benchmarks do Gemma 2B and Qwen2-72B share?
13 benchmarks have published results for both models. Gemma 2B has 23 scored results on Noometry and Qwen2-72B has 26.