Model comparison
Gemma 1.1 7b IT vs Qwen1.5-14B
Qwen1.5-14B is the stronger model overall, scoring 32.7 to 31.3 on the Noometry Index.
Last verified . 16 shared benchmarks.
Google
Alibaba (Qwen)Summary
- They share 16 benchmarks with published results for both. Gemma 1.1 7b IT scores higher in 0 categories and Qwen1.5-14B in 8 categories; 6 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Qwen1.5-14B leads 33.6 to 30.4.
Side by side
| Gemma 1.1 7b IT | Qwen1.5-14B | |
|---|---|---|
| Provider | Alibaba (Qwen) | |
| Noometry Index | 31.3 | 32.7 |
| Released | — | 2024-02-04 |
| Weights | Open | Open |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 19 | 17 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Qwen1.5-14B leads
Gemma 1.1 7b IT: 31.5 (#284), Qwen1.5-14B: 33.1 (#263)
| Benchmark | Gemma 1.1 7b IT | Qwen1.5-14B |
|---|---|---|
| LMArena Coding | 1084 | 1138 |
| HumanEval+ | 35.4% | — |
| MBPP+ | 45% | — |
Reasoning Too close to call
Gemma 1.1 7b IT: 20.5 (#238), Qwen1.5-14B: 21.4 (#223)
| Benchmark | Gemma 1.1 7b IT | Qwen1.5-14B |
|---|---|---|
| LMArena Hard Prompts | 1071 | 1113 |
Math Too close to call
Gemma 1.1 7b IT: 32.0 (#220), Qwen1.5-14B: 32.4 (#215)
| Benchmark | Gemma 1.1 7b IT | Qwen1.5-14B |
|---|---|---|
| LMArena Math | 1107 | 1125 |
Knowledge Qwen1.5-14B leads
Gemma 1.1 7b IT: 28.3 (#247), Qwen1.5-14B: 29.8 (#232)
| Benchmark | Gemma 1.1 7b IT | Qwen1.5-14B |
|---|---|---|
| LMArena Expert | 1039 | 1094 |
| MMLU | — | 68.6% |
Multilingual Qwen1.5-14B leads
Gemma 1.1 7b IT: 28.1 (#273), Qwen1.5-14B: 30.7 (#262)
| Benchmark | Gemma 1.1 7b IT | Qwen1.5-14B |
|---|---|---|
| LMArena Non-English | 1052 | 1095 |
| LMArena Chinese | 1061 | 1147 |
| LMArena French | 1065 | 1116 |
| LMArena German | 1054 | 1043 |
| LMArena Japanese | 971 | 1019 |
| LMArena Russian | 1046 | 1046 |
| LMArena Spanish | 1049 | 1085 |
| LMArena Korean | 988 | — |
Instruction Following Qwen1.5-14B leads
Gemma 1.1 7b IT: 54.0 (#283), Qwen1.5-14B: 56.8 (#271)
| Benchmark | Gemma 1.1 7b IT | Qwen1.5-14B |
|---|---|---|
| LMArena Instruction Following | 1057 | 1102 |
Long Context Qwen1.5-14B leads
Gemma 1.1 7b IT: 32.1 (#272), Qwen1.5-14B: 33.7 (#257)
| Benchmark | Gemma 1.1 7b IT | Qwen1.5-14B |
|---|---|---|
| LMArena Longer Query | 1056 | 1113 |
Writing & Preference Qwen1.5-14B leads
Gemma 1.1 7b IT: 30.4 (#288), Qwen1.5-14B: 33.6 (#276)
| Benchmark | Gemma 1.1 7b IT | Qwen1.5-14B |
|---|---|---|
| LMArena Text | 1094 | 1128 |
| LMArena Creative Writing | 1060 | 1091 |
| LMArena Multi-Turn | 1040 | 1110 |
Frequently asked questions
Is Gemma 1.1 7b IT better than Qwen1.5-14B?
Qwen1.5-14B is the stronger model overall, scoring 32.7 to 31.3 on the Noometry Index.
Is Gemma 1.1 7b IT or Qwen1.5-14B better for coding?
Qwen1.5-14B scores higher on coding benchmarks: 33.1 versus 31.5 in the Noometry coding category.
How many benchmarks do Gemma 1.1 7b IT and Qwen1.5-14B share?
16 benchmarks have published results for both models. Gemma 1.1 7b IT has 19 scored results on Noometry and Qwen1.5-14B has 17.