Model comparison
Gemma 3n E4b IT vs Qwen1.5-72B
Gemma 3n E4b IT is the stronger model overall, scoring 37.3 to 30.8 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 Qwen1.5-72B 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 11.5.
Side by side
| Gemma 3n E4b IT | Qwen1.5-72B | |
|---|---|---|
| Provider | Alibaba (Qwen) | |
| Noometry Index | 37.3 | 30.8 |
| Released | — | 2024-02-04 |
| Weights | Open | Open |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 18 | 22 |
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), Qwen1.5-72B: 31.9 (#277)
| Benchmark | Gemma 3n E4b IT | Qwen1.5-72B |
|---|---|---|
| LMArena Coding | 1268 | 1165 |
| BigCodeBench Instruct | — | 33.2% |
| BigCodeBench Complete | — | 40.3% |
| HumanEval+ | — | 59.1% |
| MBPP+ | — | 61.6% |
Reasoning Qwen1.5-72B leads
Gemma 3n E4b IT: 19.9 (#247), Qwen1.5-72B: 22.2 (#203)
| Benchmark | Gemma 3n E4b IT | Qwen1.5-72B |
|---|---|---|
| LMArena Hard Prompts | 1284 | 1148 |
| Kagi LLM Benchmark | 31.5% | — |
Math Gemma 3n E4b IT leads
Gemma 3n E4b IT: 35.1 (#188), Qwen1.5-72B: 33.2 (#205)
| Benchmark | Gemma 3n E4b IT | Qwen1.5-72B |
|---|---|---|
| LMArena Math | 1251 | 1164 |
Knowledge Gemma 3n E4b IT leads
Gemma 3n E4b IT: 34.2 (#198), Qwen1.5-72B: 11.5 (#300)
| Benchmark | Gemma 3n E4b IT | Qwen1.5-72B |
|---|---|---|
| LMArena Expert | 1246 | 1136 |
| GPQA Diamond | — | 28.8% |
Multilingual Gemma 3n E4b IT leads
Gemma 3n E4b IT: 43.4 (#183), Qwen1.5-72B: 33.2 (#253)
| Benchmark | Gemma 3n E4b IT | Qwen1.5-72B |
|---|---|---|
| LMArena Non-English | 1285 | 1135 |
| LMArena Chinese | 1309 | 1186 |
| LMArena French | 1330 | 1159 |
| LMArena German | 1311 | 1084 |
| LMArena Japanese | 1272 | 1061 |
| LMArena Korean | 1259 | 1050 |
| LMArena Russian | 1288 | 1104 |
| LMArena Spanish | 1305 | 1110 |
Instruction Following Gemma 3n E4b IT leads
Gemma 3n E4b IT: 66.1 (#210), Qwen1.5-72B: 59.3 (#256)
| Benchmark | Gemma 3n E4b IT | Qwen1.5-72B |
|---|---|---|
| LMArena Instruction Following | 1255 | 1141 |
Long Context Gemma 3n E4b IT leads
Gemma 3n E4b IT: 38.7 (#191), Qwen1.5-72B: 35.1 (#243)
| Benchmark | Gemma 3n E4b IT | Qwen1.5-72B |
|---|---|---|
| LMArena Longer Query | 1276 | 1157 |
Writing & Preference Gemma 3n E4b IT leads
Gemma 3n E4b IT: 50.1 (#186), Qwen1.5-72B: 37.3 (#258)
| Benchmark | Gemma 3n E4b IT | Qwen1.5-72B |
|---|---|---|
| LMArena Text | 1306 | 1166 |
| LMArena Creative Writing | 1287 | 1137 |
| LMArena Multi-Turn | 1276 | 1160 |
Frequently asked questions
Is Gemma 3n E4b IT better than Qwen1.5-72B?
Gemma 3n E4b IT is the stronger model overall, scoring 37.3 to 30.8 on the Noometry Index.
Is Gemma 3n E4b IT or Qwen1.5-72B better for coding?
Gemma 3n E4b IT scores higher on coding benchmarks: 37.0 versus 31.9 in the Noometry coding category.
How many benchmarks do Gemma 3n E4b IT and Qwen1.5-72B share?
17 benchmarks have published results for both models. Gemma 3n E4b IT has 18 scored results on Noometry and Qwen1.5-72B has 22.