Model comparison
Gemma 2 27B vs Qwen2.5-Max
Qwen2.5-Max is the stronger model overall, scoring 40.7 to 29.4 on the Noometry Index.
Last verified . 26 shared benchmarks.
Google
Alibaba (Qwen)Summary
- They share 26 benchmarks with published results for both. Gemma 2 27B scores higher in 0 categories and Qwen2.5-Max in 8 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in math, where Qwen2.5-Max leads 36.9 to 10.7.
- The biggest single-benchmark swing is LiveBench Math: 26.5% for Gemma 2 27B and 58.4% for Qwen2.5-Max.
- Gemma 2 27B has downloadable open weights; the other is API-only.
Side by side
| Gemma 2 27B | Qwen2.5-Max | |
|---|---|---|
| Provider | Alibaba (Qwen) | |
| Noometry Index | 29.4 | 40.7 |
| Released | 2024-06-24 | 2025-01-25 |
| Weights | Open | Proprietary |
| Context window | 8K | — |
| Max output | 2K | — |
| Input $ / M tokens | $0.65 | — |
| Output $ / M tokens | $0.65 | — |
| Results tracked | 34 | 27 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Qwen2.5-Max leads
Gemma 2 27B: 34.1 (#246), Qwen2.5-Max: 41.8 (#117)
| Benchmark | Gemma 2 27B | Qwen2.5-Max |
|---|---|---|
| LiveBench Coding | 36% | 64.4% |
| LMArena Coding | 1211 | 1359 |
| BigCodeBench Instruct | 42.8% | — |
| BigCodeBench Complete | 52.5% | — |
Reasoning Qwen2.5-Max leads
Gemma 2 27B: 15.3 (#315), Qwen2.5-Max: 25.6 (#147)
| Benchmark | Gemma 2 27B | Qwen2.5-Max |
|---|---|---|
| LiveBench Reasoning | 28.1% | 51.4% |
| LMArena Hard Prompts | 1198 | 1360 |
| LiveBench Data Analysis | 47.9% | 67.9% |
| Epoch Capabilities Index | 122.08 | 132.53 |
| LiveBench | 38.2% | 62.3% |
| DTBench | 48% | — |
| LMCA | 7.1% | — |
Math Qwen2.5-Max leads
Gemma 2 27B: 10.7 (#311), Qwen2.5-Max: 36.9 (#162)
| Benchmark | Gemma 2 27B | Qwen2.5-Max |
|---|---|---|
| LiveBench Math | 26.5% | 58.4% |
| LMArena Math | 1212 | 1369 |
| OTIS Mock AIME 2024-2025 | 1.4% | — |
| MATH Level 5 | 27.9% | — |
Knowledge Qwen2.5-Max leads
Gemma 2 27B: 19.0 (#280), Qwen2.5-Max: 35.3 (#186)
| Benchmark | Gemma 2 27B | Qwen2.5-Max |
|---|---|---|
| Confabulations | 27.1% | 21.8% |
| LMArena Expert | 1172 | 1337 |
| GPQA Diamond | 36.5% | — |
| MMLU | 75.7% | — |
Multilingual Qwen2.5-Max leads
Gemma 2 27B: 38.6 (#226), Qwen2.5-Max: 48.1 (#146)
| Benchmark | Gemma 2 27B | Qwen2.5-Max |
|---|---|---|
| LMArena Non-English | 1217 | 1352 |
| LMArena Chinese | 1221 | 1382 |
| LMArena French | 1247 | 1396 |
| LMArena German | 1209 | 1350 |
| LMArena Japanese | 1175 | 1300 |
| LMArena Korean | 1174 | 1304 |
| LMArena Russian | 1234 | 1353 |
| LMArena Spanish | 1228 | 1377 |
Instruction Following Qwen2.5-Max leads
Gemma 2 27B: 60.5 (#249), Qwen2.5-Max: 71.3 (#152)
| Benchmark | Gemma 2 27B | Qwen2.5-Max |
|---|---|---|
| LiveBench Instruction Following | 58.1% | 75.3% |
| LMArena Instruction Following | 1206 | 1335 |
Long Context Qwen2.5-Max leads
Gemma 2 27B: 37.3 (#218), Qwen2.5-Max: 41.4 (#142)
| Benchmark | Gemma 2 27B | Qwen2.5-Max |
|---|---|---|
| LMArena Longer Query | 1231 | 1358 |
Writing & Preference Qwen2.5-Max leads
Gemma 2 27B: 44.2 (#225), Qwen2.5-Max: 55.4 (#146)
| Benchmark | Gemma 2 27B | Qwen2.5-Max |
|---|---|---|
| LMArena Text | 1231 | 1367 |
| LMArena Creative Writing | 1241 | 1339 |
| LMArena Multi-Turn | 1224 | 1364 |
| LiveBench Language | 32.6% | 56.3% |
| Short-Story Creative Writing | — | 72.9% |
Frequently asked questions
Is Gemma 2 27B better than Qwen2.5-Max?
Qwen2.5-Max is the stronger model overall, scoring 40.7 to 29.4 on the Noometry Index.
Is Gemma 2 27B or Qwen2.5-Max better for coding?
Qwen2.5-Max scores higher on coding benchmarks: 41.8 versus 34.1 in the Noometry coding category.
How many benchmarks do Gemma 2 27B and Qwen2.5-Max share?
26 benchmarks have published results for both models. Gemma 2 27B has 34 scored results on Noometry and Qwen2.5-Max has 27.