Model comparison
Gemma 7B vs Qwen2.5-Max
Qwen2.5-Max is the stronger model overall, scoring 40.7 to 30.0 on the Noometry Index.
Last verified . 14 shared benchmarks.
Google
Alibaba (Qwen)Summary
- They share 14 benchmarks with published results for both. Gemma 7B scores higher in 0 categories and Qwen2.5-Max in 8 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Qwen2.5-Max leads 55.4 to 27.1.
- Gemma 7B has downloadable open weights; the other is API-only.
Side by side
| Gemma 7B | Qwen2.5-Max | |
|---|---|---|
| Provider | Alibaba (Qwen) | |
| Noometry Index | 30.0 | 40.7 |
| Released | 2024-02-21 | 2025-01-25 |
| Weights | Open | Proprietary |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 27 | 27 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Qwen2.5-Max leads
Gemma 7B: 30.5 (#294), Qwen2.5-Max: 41.8 (#117)
| Benchmark | Gemma 7B | Qwen2.5-Max |
|---|---|---|
| LMArena Coding | 1048 | 1359 |
| LiveBench Coding | — | 64.4% |
| HumanEval+ | 28.7% | — |
| MBPP+ | 43.4% | — |
Reasoning Qwen2.5-Max leads
Gemma 7B: 19.9 (#249), Qwen2.5-Max: 25.6 (#147)
| Benchmark | Gemma 7B | Qwen2.5-Max |
|---|---|---|
| LMArena Hard Prompts | 1042 | 1360 |
| Epoch Capabilities Index | 111.99 | 132.53 |
| LiveBench Reasoning | — | 51.4% |
| LiveBench Data Analysis | — | 67.9% |
| Adversarial NLI | 48.7% | — |
| BIG-Bench Hard | 55.1% | — |
| HellaSwag | 82.2% | — |
| LiveBench | — | 62.3% |
| PIQA | 81.2% | — |
| WinoGrande | 79% | — |
Math Qwen2.5-Max leads
Gemma 7B: 31.2 (#228), Qwen2.5-Max: 36.9 (#162)
| Benchmark | Gemma 7B | Qwen2.5-Max |
|---|---|---|
| LMArena Math | 1066 | 1369 |
| LiveBench Math | — | 58.4% |
| GSM8K | 46.4% | — |
Knowledge Qwen2.5-Max leads
Gemma 7B: 27.3 (#252), Qwen2.5-Max: 35.3 (#186)
| Benchmark | Gemma 7B | Qwen2.5-Max |
|---|---|---|
| LMArena Expert | 1001 | 1337 |
| Confabulations | — | 21.8% |
| ARC (AI2) Challenge | 78.3% | — |
| BoolQ | 83.2% | — |
| MMLU | 66.1% | — |
| OpenBookQA | 78.6% | — |
| TriviaQA | 72.3% | — |
Multilingual Qwen2.5-Max leads
Gemma 7B: 25.1 (#287), Qwen2.5-Max: 48.1 (#146)
| Benchmark | Gemma 7B | Qwen2.5-Max |
|---|---|---|
| LMArena Non-English | 999 | 1352 |
| LMArena Chinese | 1035 | 1382 |
| LMArena French | 1025 | 1396 |
| LMArena Russian | 993 | 1353 |
| LMArena German | — | 1350 |
| LMArena Japanese | — | 1300 |
| LMArena Korean | — | 1304 |
| LMArena Spanish | — | 1377 |
Instruction Following Qwen2.5-Max leads
Gemma 7B: 51.5 (#295), Qwen2.5-Max: 71.3 (#152)
| Benchmark | Gemma 7B | Qwen2.5-Max |
|---|---|---|
| LMArena Instruction Following | 1017 | 1335 |
| LiveBench Instruction Following | — | 75.3% |
Long Context Qwen2.5-Max leads
Gemma 7B: 31.1 (#282), Qwen2.5-Max: 41.4 (#142)
| Benchmark | Gemma 7B | Qwen2.5-Max |
|---|---|---|
| LMArena Longer Query | 1022 | 1358 |
Writing & Preference Qwen2.5-Max leads
Gemma 7B: 27.1 (#302), Qwen2.5-Max: 55.4 (#146)
| Benchmark | Gemma 7B | Qwen2.5-Max |
|---|---|---|
| LMArena Text | 1056 | 1367 |
| LMArena Creative Writing | 1024 | 1339 |
| LMArena Multi-Turn | 963 | 1364 |
| Short-Story Creative Writing | — | 72.9% |
| LiveBench Language | — | 56.3% |
Frequently asked questions
Is Gemma 7B better than Qwen2.5-Max?
Qwen2.5-Max is the stronger model overall, scoring 40.7 to 30.0 on the Noometry Index.
Is Gemma 7B or Qwen2.5-Max better for coding?
Qwen2.5-Max scores higher on coding benchmarks: 41.8 versus 30.5 in the Noometry coding category.
How many benchmarks do Gemma 7B and Qwen2.5-Max share?
14 benchmarks have published results for both models. Gemma 7B has 27 scored results on Noometry and Qwen2.5-Max has 27.