Model comparison
Gemma 3n E4b IT vs Qwen2-72B
Gemma 3n E4b IT is the stronger model overall, scoring 37.3 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 3n E4b IT scores higher in 7 categories and Qwen2-72B in 1 category; 8 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Gemma 3n E4b IT leads 34.2 to 21.2.
Side by side
| Gemma 3n E4b IT | Qwen2-72B | |
|---|---|---|
| Provider | Alibaba (Qwen) | |
| Noometry Index | 37.3 | 30.0 |
| Released | — | 2024-06-07 |
| Weights | Open | Open |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 18 | 26 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Gemma 3n E4b IT leads
Gemma 3n E4b IT: 37.0 (#198), Qwen2-72B: 29.1 (#310)
| Benchmark | Gemma 3n E4b IT | Qwen2-72B |
|---|---|---|
| LMArena Coding | 1268 | 1196 |
| WeirdML | — | 11.3% |
| BigCodeBench Instruct | — | 38.5% |
| BigCodeBench Complete | — | 54% |
Agentic & Tool Use Not comparable
Gemma 3n E4b IT: —, Qwen2-72B: 17.0 (#146)
| Benchmark | Gemma 3n E4b IT | Qwen2-72B |
|---|---|---|
| TheAgentCompany | — | 1.1% |
| METR Time Horizons | — | 29.9% |
Reasoning Qwen2-72B leads
Gemma 3n E4b IT: 19.9 (#247), Qwen2-72B: 23.2 (#181)
| Benchmark | Gemma 3n E4b IT | Qwen2-72B |
|---|---|---|
| LMArena Hard Prompts | 1284 | 1191 |
| Kagi LLM Benchmark | 31.5% | — |
| Epoch Capabilities Index | — | 125.28 |
Math Gemma 3n E4b IT leads
Gemma 3n E4b IT: 35.1 (#188), Qwen2-72B: 30.2 (#236)
| Benchmark | Gemma 3n E4b IT | Qwen2-72B |
|---|---|---|
| LMArena Math | 1251 | 1235 |
| MATH Level 5 | — | 39.1% |
Knowledge Gemma 3n E4b IT leads
Gemma 3n E4b IT: 34.2 (#198), Qwen2-72B: 21.2 (#275)
| Benchmark | Gemma 3n E4b IT | Qwen2-72B |
|---|---|---|
| LMArena Expert | 1246 | 1171 |
| GPQA Diamond | — | 40.8% |
| MMLU | — | 82.4% |
Multilingual Gemma 3n E4b IT leads
Gemma 3n E4b IT: 43.4 (#183), Qwen2-72B: 35.9 (#244)
| Benchmark | Gemma 3n E4b IT | Qwen2-72B |
|---|---|---|
| LMArena Non-English | 1285 | 1176 |
| LMArena Chinese | 1309 | 1240 |
| LMArena French | 1330 | 1170 |
| LMArena German | 1311 | 1151 |
| LMArena Japanese | 1272 | 1111 |
| LMArena Korean | 1259 | 1083 |
| LMArena Russian | 1288 | 1169 |
| LMArena Spanish | 1305 | 1169 |
Instruction Following Gemma 3n E4b IT leads
Gemma 3n E4b IT: 66.1 (#210), Qwen2-72B: 61.7 (#241)
| Benchmark | Gemma 3n E4b IT | Qwen2-72B |
|---|---|---|
| LMArena Instruction Following | 1255 | 1181 |
Long Context Gemma 3n E4b IT leads
Gemma 3n E4b IT: 38.7 (#191), Qwen2-72B: 36.1 (#235)
| Benchmark | Gemma 3n E4b IT | Qwen2-72B |
|---|---|---|
| LMArena Longer Query | 1276 | 1192 |
Writing & Preference Gemma 3n E4b IT leads
Gemma 3n E4b IT: 50.1 (#186), Qwen2-72B: 40.8 (#241)
| Benchmark | Gemma 3n E4b IT | Qwen2-72B |
|---|---|---|
| LMArena Text | 1306 | 1203 |
| LMArena Creative Writing | 1287 | 1181 |
| LMArena Multi-Turn | 1276 | 1196 |
Frequently asked questions
Is Gemma 3n E4b IT better than Qwen2-72B?
Gemma 3n E4b IT is the stronger model overall, scoring 37.3 to 30.0 on the Noometry Index.
Is Gemma 3n E4b IT or Qwen2-72B better for coding?
Gemma 3n E4b IT scores higher on coding benchmarks: 37.0 versus 29.1 in the Noometry coding category.
How many benchmarks do Gemma 3n E4b IT and Qwen2-72B share?
17 benchmarks have published results for both models. Gemma 3n E4b IT has 18 scored results on Noometry and Qwen2-72B has 26.