Model comparison
Gemma 1.1 7b IT vs Qwen1.5-72B
Gemma 1.1 7b IT and Qwen1.5-72B score almost the same on the Noometry Index (31.3 vs 30.8), so choose on price, context window or the category you care about most.
Last verified . 19 shared benchmarks.
Google
Alibaba (Qwen)Summary
- They share 19 benchmarks with published results for both. Gemma 1.1 7b IT scores higher in 1 category and Qwen1.5-72B in 7 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Gemma 1.1 7b IT leads 28.3 to 11.5.
Side by side
| Gemma 1.1 7b IT | Qwen1.5-72B | |
|---|---|---|
| Provider | Alibaba (Qwen) | |
| Noometry Index | 31.3 | 30.8 |
| Released | — | 2024-02-04 |
| Weights | Open | Open |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 19 | 22 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Too close to call
Gemma 1.1 7b IT: 31.5 (#284), Qwen1.5-72B: 31.9 (#277)
| Benchmark | Gemma 1.1 7b IT | Qwen1.5-72B |
|---|---|---|
| LMArena Coding | 1084 | 1165 |
| HumanEval+ | 35.4% | 59.1% |
| MBPP+ | 45% | 61.6% |
| BigCodeBench Instruct | — | 33.2% |
| BigCodeBench Complete | — | 40.3% |
Reasoning Qwen1.5-72B leads
Gemma 1.1 7b IT: 20.5 (#238), Qwen1.5-72B: 22.2 (#203)
| Benchmark | Gemma 1.1 7b IT | Qwen1.5-72B |
|---|---|---|
| LMArena Hard Prompts | 1071 | 1148 |
Math Qwen1.5-72B leads
Gemma 1.1 7b IT: 32.0 (#220), Qwen1.5-72B: 33.2 (#205)
| Benchmark | Gemma 1.1 7b IT | Qwen1.5-72B |
|---|---|---|
| LMArena Math | 1107 | 1164 |
Knowledge Gemma 1.1 7b IT leads
Gemma 1.1 7b IT: 28.3 (#247), Qwen1.5-72B: 11.5 (#300)
| Benchmark | Gemma 1.1 7b IT | Qwen1.5-72B |
|---|---|---|
| LMArena Expert | 1039 | 1136 |
| GPQA Diamond | — | 28.8% |
Multilingual Qwen1.5-72B leads
Gemma 1.1 7b IT: 28.1 (#273), Qwen1.5-72B: 33.2 (#253)
| Benchmark | Gemma 1.1 7b IT | Qwen1.5-72B |
|---|---|---|
| LMArena Non-English | 1052 | 1135 |
| LMArena Chinese | 1061 | 1186 |
| LMArena French | 1065 | 1159 |
| LMArena German | 1054 | 1084 |
| LMArena Japanese | 971 | 1061 |
| LMArena Korean | 988 | 1050 |
| LMArena Russian | 1046 | 1104 |
| LMArena Spanish | 1049 | 1110 |
Instruction Following Qwen1.5-72B leads
Gemma 1.1 7b IT: 54.0 (#283), Qwen1.5-72B: 59.3 (#256)
| Benchmark | Gemma 1.1 7b IT | Qwen1.5-72B |
|---|---|---|
| LMArena Instruction Following | 1057 | 1141 |
Long Context Qwen1.5-72B leads
Gemma 1.1 7b IT: 32.1 (#272), Qwen1.5-72B: 35.1 (#243)
| Benchmark | Gemma 1.1 7b IT | Qwen1.5-72B |
|---|---|---|
| LMArena Longer Query | 1056 | 1157 |
Writing & Preference Qwen1.5-72B leads
Gemma 1.1 7b IT: 30.4 (#288), Qwen1.5-72B: 37.3 (#258)
| Benchmark | Gemma 1.1 7b IT | Qwen1.5-72B |
|---|---|---|
| LMArena Text | 1094 | 1166 |
| LMArena Creative Writing | 1060 | 1137 |
| LMArena Multi-Turn | 1040 | 1160 |
Frequently asked questions
Is Gemma 1.1 7b IT better than Qwen1.5-72B?
Gemma 1.1 7b IT and Qwen1.5-72B score almost the same on the Noometry Index (31.3 vs 30.8), so choose on price, context window or the category you care about most.
Is Gemma 1.1 7b IT or Qwen1.5-72B better for coding?
They score almost the same on coding (31.5 vs 31.9); test both on your own repository before choosing.
How many benchmarks do Gemma 1.1 7b IT and Qwen1.5-72B share?
19 benchmarks have published results for both models. Gemma 1.1 7b IT has 19 scored results on Noometry and Qwen1.5-72B has 22.