Model comparison
Gemma 2 9B vs Qwen1.5-14B
Qwen1.5-14B is the stronger model overall, scoring 32.7 to 25.9 on the Noometry Index.
Last verified . 17 shared benchmarks.
Google
Alibaba (Qwen)Summary
- They share 17 benchmarks with published results for both. Gemma 2 9B scores higher in 3 categories and Qwen1.5-14B in 5 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in math, where Qwen1.5-14B leads 32.4 to 9.9.
Side by side
| Gemma 2 9B | Qwen1.5-14B | |
|---|---|---|
| Provider | Alibaba (Qwen) | |
| Noometry Index | 25.9 | 32.7 |
| Released | 2024-06-24 | 2024-02-04 |
| Weights | Open | Open |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 35 | 17 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Qwen1.5-14B leads
Gemma 2 9B: 29.4 (#304), Qwen1.5-14B: 33.1 (#263)
| Benchmark | Gemma 2 9B | Qwen1.5-14B |
|---|---|---|
| LMArena Coding | 1173 | 1138 |
| BigCodeBench Instruct | 34.7% | — |
| LiveBench Coding | 22.5% | — |
| BigCodeBench Complete | 40.6% | — |
Reasoning Qwen1.5-14B leads
Gemma 2 9B: 15.9 (#309), Qwen1.5-14B: 21.4 (#223)
| Benchmark | Gemma 2 9B | Qwen1.5-14B |
|---|---|---|
| LMArena Hard Prompts | 1171 | 1113 |
| LiveBench Reasoning | 15.2% | — |
| LiveBench Data Analysis | 36.4% | — |
| Epoch Capabilities Index | 119.83 | — |
| LiveBench | 28.7% | — |
| PIQA | 83.7% | — |
Math Qwen1.5-14B leads
Gemma 2 9B: 9.9 (#318), Qwen1.5-14B: 32.4 (#215)
| Benchmark | Gemma 2 9B | Qwen1.5-14B |
|---|---|---|
| LMArena Math | 1183 | 1125 |
| OTIS Mock AIME 2024-2025 | 0.6% | — |
| LiveBench Math | 19.8% | — |
| MATH Level 5 | 21% | — |
| GSM8K | 84.9% | — |
Knowledge Qwen1.5-14B leads
Gemma 2 9B: 9.7 (#305), Qwen1.5-14B: 29.8 (#232)
| Benchmark | Gemma 2 9B | Qwen1.5-14B |
|---|---|---|
| LMArena Expert | 1147 | 1094 |
| MMLU | 72.1% | 68.6% |
| GPQA Diamond | 27.5% | — |
| BoolQ | 85.7% | — |
Multilingual Gemma 2 9B leads
Gemma 2 9B: 36.6 (#238), Qwen1.5-14B: 30.7 (#262)
| Benchmark | Gemma 2 9B | Qwen1.5-14B |
|---|---|---|
| LMArena Non-English | 1188 | 1095 |
| LMArena Chinese | 1185 | 1147 |
| LMArena French | 1190 | 1116 |
| LMArena German | 1186 | 1043 |
| LMArena Japanese | 1144 | 1019 |
| LMArena Russian | 1200 | 1046 |
| LMArena Spanish | 1200 | 1085 |
| LMArena Korean | 1137 | — |
Instruction Following Too close to call
Gemma 2 9B: 57.6 (#269), Qwen1.5-14B: 56.8 (#271)
| Benchmark | Gemma 2 9B | Qwen1.5-14B |
|---|---|---|
| LMArena Instruction Following | 1178 | 1102 |
| LiveBench Instruction Following | 52.6% | — |
Long Context Gemma 2 9B leads
Gemma 2 9B: 36.3 (#233), Qwen1.5-14B: 33.7 (#257)
| Benchmark | Gemma 2 9B | Qwen1.5-14B |
|---|---|---|
| LMArena Longer Query | 1197 | 1113 |
Writing & Preference Qwen1.5-14B leads
Gemma 2 9B: 32.1 (#281), Qwen1.5-14B: 33.6 (#276)
| Benchmark | Gemma 2 9B | Qwen1.5-14B |
|---|---|---|
| LMArena Text | 1207 | 1128 |
| LMArena Creative Writing | 1206 | 1091 |
| LMArena Multi-Turn | 1193 | 1110 |
| EQ-Bench Creative Writing | 841 | — |
| LiveBench Language | 25.5% | — |
Frequently asked questions
Is Gemma 2 9B better than Qwen1.5-14B?
Qwen1.5-14B is the stronger model overall, scoring 32.7 to 25.9 on the Noometry Index.
Is Gemma 2 9B or Qwen1.5-14B better for coding?
Qwen1.5-14B scores higher on coding benchmarks: 33.1 versus 29.4 in the Noometry coding category.
How many benchmarks do Gemma 2 9B and Qwen1.5-14B share?
17 benchmarks have published results for both models. Gemma 2 9B has 35 scored results on Noometry and Qwen1.5-14B has 17.