Model comparison
Gemma 2 9B vs Qwen2-72B
Qwen2-72B is the stronger model overall, scoring 29.5 to 25.7 on the Noometry Index.
Last verified . 23 shared benchmarks.
Google
Alibaba (Qwen)Summary
- They share 23 benchmarks with published results for both. Gemma 2 9B scores higher in 3 categories and Qwen2-72B in 5 categories; 5 gaps are clear of the uncertainty.
- The widest gap is in math, where Qwen2-72B leads 27.9 to 9.3.
- The biggest single-benchmark swing is MATH Level 5: 21% for Gemma 2 9B and 39.1% for Qwen2-72B.
Side by side
| Gemma 2 9B | Qwen2-72B | |
|---|---|---|
| Provider | Alibaba (Qwen) | |
| Noometry Index | 25.7 | 29.5 |
| Released | 2024-06-24 | 2024-06-07 |
| Weights | Open | Open |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 35 | 26 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Too close to call
Gemma 2 9B: 29.0 (#299), Qwen2-72B: 28.7 (#303)
| Benchmark | Gemma 2 9B | Qwen2-72B |
|---|---|---|
| BigCodeBench Instruct | 34.7% | 38.5% |
| LMArena Coding | 1174 | 1196 |
| BigCodeBench Complete | 40.6% | 54% |
| WeirdML | — | 11.3% |
| LiveBench Coding | 22.5% | — |
Agentic & Tool Use Not comparable
Gemma 2 9B: —, Qwen2-72B: 16.9 (#138)
| Benchmark | Gemma 2 9B | Qwen2-72B |
|---|---|---|
| TheAgentCompany | — | 1.1% |
| METR Time Horizons | — | 29.9% |
Reasoning Qwen2-72B leads
Gemma 2 9B: 15.3 (#306), Qwen2-72B: 22.2 (#184)
| Benchmark | Gemma 2 9B | Qwen2-72B |
|---|---|---|
| LMArena Hard Prompts | 1172 | 1191 |
| Epoch Capabilities Index | 119.78 | 125.27 |
| LiveBench Reasoning | 15.2% | — |
| LiveBench Data Analysis | 36.4% | — |
| LiveBench | 28.7% | — |
| PIQA | 83.7% | — |
Math Qwen2-72B leads
Gemma 2 9B: 9.3 (#312), Qwen2-72B: 27.9 (#232)
| Benchmark | Gemma 2 9B | Qwen2-72B |
|---|---|---|
| LMArena Math | 1183 | 1235 |
| MATH Level 5 | 21% | 39.1% |
| OTIS Mock AIME 2024-2025 | 0.6% | — |
| LiveBench Math | 19.8% | — |
| GSM8K | 84.9% | — |
Knowledge Qwen2-72B leads
Gemma 2 9B: 9.7 (#300), Qwen2-72B: 21.2 (#270)
| Benchmark | Gemma 2 9B | Qwen2-72B |
|---|---|---|
| GPQA Diamond | 27.5% | 40.8% |
| LMArena Expert | 1147 | 1171 |
| MMLU | 72.1% | 82.4% |
| BoolQ | 85.7% | — |
Multilingual Too close to call
Gemma 2 9B: 36.8 (#233), Qwen2-72B: 36.0 (#239)
| Benchmark | Gemma 2 9B | Qwen2-72B |
|---|---|---|
| LMArena Non-English | 1188 | 1176 |
| LMArena Chinese | 1185 | 1240 |
| LMArena French | 1189 | 1169 |
| LMArena German | 1186 | 1151 |
| LMArena Japanese | 1144 | 1111 |
| LMArena Korean | 1137 | 1083 |
| LMArena Russian | 1200 | 1169 |
| LMArena Spanish | 1200 | 1168 |
Instruction Following Qwen2-72B leads
Gemma 2 9B: 57.8 (#264), Qwen2-72B: 62.0 (#236)
| Benchmark | Gemma 2 9B | Qwen2-72B |
|---|---|---|
| LMArena Instruction Following | 1178 | 1181 |
| LiveBench Instruction Following | 52.6% | — |
Long Context Too close to call
Gemma 2 9B: 36.3 (#228), Qwen2-72B: 36.1 (#230)
| Benchmark | Gemma 2 9B | Qwen2-72B |
|---|---|---|
| LMArena Longer Query | 1197 | 1193 |
Writing & Preference Qwen2-72B leads
Gemma 2 9B: 32.3 (#276), Qwen2-72B: 41.0 (#236)
| Benchmark | Gemma 2 9B | Qwen2-72B |
|---|---|---|
| LMArena Text | 1207 | 1203 |
| LMArena Creative Writing | 1206 | 1181 |
| LMArena Multi-Turn | 1193 | 1195 |
| EQ-Bench Creative Writing | 841 | — |
| LiveBench Language | 25.5% | — |
Frequently asked questions
Is Gemma 2 9B better than Qwen2-72B?
Qwen2-72B is the stronger model overall, scoring 29.5 to 25.7 on the Noometry Index.
Is Gemma 2 9B or Qwen2-72B better for coding?
They score almost the same on coding (29.0 vs 28.7); test both on your own repository before choosing.
How many benchmarks do Gemma 2 9B and Qwen2-72B share?
23 benchmarks have published results for both models. Gemma 2 9B has 35 scored results on Noometry and Qwen2-72B has 26.