Model comparison
Gemma 7B vs Qwen2.5-Coder-32B
Qwen2.5-Coder-32B is the stronger model overall, scoring 32.9 to 29.5 on the Noometry Index.
Last verified . 20 shared benchmarks.
Google
Alibaba (Qwen)Summary
- They share 20 benchmarks with published results for both. Gemma 7B scores higher in 1 category and Qwen2.5-Coder-32B in 7 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Qwen2.5-Coder-32B leads 41.8 to 27.2.
Side by side
| Gemma 7B | Qwen2.5-Coder-32B | |
|---|---|---|
| Provider | Alibaba (Qwen) | |
| Noometry Index | 29.5 | 32.9 |
| Released | 2024-02-21 | 2024-09-18 |
| Weights | Open | Open |
| Context window | — | 33K |
| Max output | — | 29K |
| Input $ / M tokens | — | $0.66 |
| Output $ / M tokens | — | $1 |
| Results tracked | 27 | 31 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Gemma 7B leads
Gemma 7B: 29.9 (#290), Qwen2.5-Coder-32B: 22.4 (#328)
| Benchmark | Gemma 7B | Qwen2.5-Coder-32B |
|---|---|---|
| LMArena Coding | 1048 | 1276 |
| HumanEval+ | 28.7% | 87.2% |
| MBPP+ | 43.4% | 77% |
| SWE-bench Verified (bash only) | — | 9% |
| Aider Polyglot | — | 16.4% |
| BigCodeBench Instruct | — | 49% |
| LiveBench Coding | — | 56.9% |
| BigCodeBench Complete | — | 58% |
Reasoning Qwen2.5-Coder-32B leads
Gemma 7B: 19.0 (#247), Qwen2.5-Coder-32B: 20.4 (#220)
| Benchmark | Gemma 7B | Qwen2.5-Coder-32B |
|---|---|---|
| LMArena Hard Prompts | 1042 | 1251 |
| Epoch Capabilities Index | 111.74 | 119.41 |
| HellaSwag | 82.2% | 83% |
| WinoGrande | 79% | 80.8% |
| LiveBench Reasoning | — | 42.1% |
| LiveBench Data Analysis | — | 49.9% |
| Adversarial NLI | 48.7% | — |
| BIG-Bench Hard | 55.1% | — |
| LiveBench | — | 46.2% |
| PIQA | 81.2% | — |
Math Qwen2.5-Coder-32B leads
Gemma 7B: 28.7 (#225), Qwen2.5-Coder-32B: 30.8 (#203)
| Benchmark | Gemma 7B | Qwen2.5-Coder-32B |
|---|---|---|
| LMArena Math | 1066 | 1251 |
| GSM8K | 46.4% | 93% |
| LiveBench Math | — | 46.6% |
Knowledge Qwen2.5-Coder-32B leads
Gemma 7B: 26.8 (#248), Qwen2.5-Coder-32B: 32.9 (#200)
| Benchmark | Gemma 7B | Qwen2.5-Coder-32B |
|---|---|---|
| LMArena Expert | 1002 | 1221 |
| ARC (AI2) Challenge | 78.3% | 70.5% |
| MMLU | 66.1% | 79.1% |
| BoolQ | 83.2% | — |
| OpenBookQA | 78.6% | — |
| TriviaQA | 72.3% | — |
Multilingual Qwen2.5-Coder-32B leads
Gemma 7B: 25.3 (#282), Qwen2.5-Coder-32B: 38.0 (#230)
| Benchmark | Gemma 7B | Qwen2.5-Coder-32B |
|---|---|---|
| LMArena Non-English | 999 | 1205 |
| LMArena Chinese | 1035 | 1222 |
| LMArena Russian | 993 | 1228 |
| LMArena French | 1024 | — |
Instruction Following Qwen2.5-Coder-32B leads
Gemma 7B: 51.7 (#290), Qwen2.5-Coder-32B: 61.6 (#240)
| Benchmark | Gemma 7B | Qwen2.5-Coder-32B |
|---|---|---|
| LMArena Instruction Following | 1017 | 1223 |
| LiveBench Instruction Following | — | 58.7% |
Long Context Qwen2.5-Coder-32B leads
Gemma 7B: 31.1 (#277), Qwen2.5-Coder-32B: 37.9 (#204)
| Benchmark | Gemma 7B | Qwen2.5-Coder-32B |
|---|---|---|
| LMArena Longer Query | 1022 | 1251 |
Writing & Preference Qwen2.5-Coder-32B leads
Gemma 7B: 27.2 (#297), Qwen2.5-Coder-32B: 41.8 (#235)
| Benchmark | Gemma 7B | Qwen2.5-Coder-32B |
|---|---|---|
| LMArena Text | 1056 | 1230 |
| LMArena Creative Writing | 1024 | 1174 |
| LMArena Multi-Turn | 963 | 1222 |
| LiveBench Language | — | 23.3% |
Frequently asked questions
Is Gemma 7B better than Qwen2.5-Coder-32B?
Qwen2.5-Coder-32B is the stronger model overall, scoring 32.9 to 29.5 on the Noometry Index.
Is Gemma 7B or Qwen2.5-Coder-32B better for coding?
Gemma 7B scores higher on coding benchmarks: 29.9 versus 22.4 in the Noometry coding category.
How many benchmarks do Gemma 7B and Qwen2.5-Coder-32B share?
20 benchmarks have published results for both models. Gemma 7B has 27 scored results on Noometry and Qwen2.5-Coder-32B has 31.