Model comparison
Gemma 2 27B vs Qwen2-72B
Gemma 2 27B and Qwen2-72B score almost the same on the Noometry Index (29.4 vs 30.0), so choose on price, context window or the category you care about most.
Last verified . 23 shared benchmarks.
Google
Alibaba (Qwen)Summary
- They share 23 benchmarks with published results for both. Gemma 2 27B scores higher in 4 categories and Qwen2-72B in 4 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in math, where Qwen2-72B leads 30.2 to 10.7.
- The biggest single-benchmark swing is MATH Level 5: 27.9% for Gemma 2 27B and 39.1% for Qwen2-72B.
Side by side
| Gemma 2 27B | Qwen2-72B | |
|---|---|---|
| Provider | Alibaba (Qwen) | |
| Noometry Index | 29.4 | 30.0 |
| Released | 2024-06-24 | 2024-06-07 |
| Weights | Open | Open |
| Context window | 8K | — |
| Max output | 2K | — |
| Input $ / M tokens | $0.65 | — |
| Output $ / M tokens | $0.65 | — |
| Results tracked | 34 | 26 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Gemma 2 27B leads
Gemma 2 27B: 34.1 (#246), Qwen2-72B: 29.1 (#310)
| Benchmark | Gemma 2 27B | Qwen2-72B |
|---|---|---|
| BigCodeBench Instruct | 42.8% | 38.5% |
| LMArena Coding | 1211 | 1196 |
| BigCodeBench Complete | 52.5% | 54% |
| WeirdML | — | 11.3% |
| LiveBench Coding | 36% | — |
Agentic & Tool Use Not comparable
Gemma 2 27B: —, Qwen2-72B: 17.0 (#146)
| Benchmark | Gemma 2 27B | Qwen2-72B |
|---|---|---|
| TheAgentCompany | — | 1.1% |
| METR Time Horizons | — | 29.9% |
Reasoning Qwen2-72B leads
Gemma 2 27B: 15.3 (#315), Qwen2-72B: 23.2 (#181)
| Benchmark | Gemma 2 27B | Qwen2-72B |
|---|---|---|
| LMArena Hard Prompts | 1198 | 1191 |
| Epoch Capabilities Index | 122.08 | 125.28 |
| LiveBench Reasoning | 28.1% | — |
| DTBench | 48% | — |
| LiveBench Data Analysis | 47.9% | — |
| LMCA | 7.1% | — |
| LiveBench | 38.2% | — |
Math Qwen2-72B leads
Gemma 2 27B: 10.7 (#311), Qwen2-72B: 30.2 (#236)
| Benchmark | Gemma 2 27B | Qwen2-72B |
|---|---|---|
| LMArena Math | 1212 | 1235 |
| MATH Level 5 | 27.9% | 39.1% |
| OTIS Mock AIME 2024-2025 | 1.4% | — |
| LiveBench Math | 26.5% | — |
Knowledge Qwen2-72B leads
Gemma 2 27B: 19.0 (#280), Qwen2-72B: 21.2 (#275)
| Benchmark | Gemma 2 27B | Qwen2-72B |
|---|---|---|
| GPQA Diamond | 36.5% | 40.8% |
| LMArena Expert | 1172 | 1171 |
| MMLU | 75.7% | 82.4% |
| Confabulations | 27.1% | — |
Multilingual Gemma 2 27B leads
Gemma 2 27B: 38.6 (#226), Qwen2-72B: 35.9 (#244)
| Benchmark | Gemma 2 27B | Qwen2-72B |
|---|---|---|
| LMArena Non-English | 1217 | 1176 |
| LMArena Chinese | 1221 | 1240 |
| LMArena French | 1247 | 1170 |
| LMArena German | 1209 | 1151 |
| LMArena Japanese | 1175 | 1111 |
| LMArena Korean | 1174 | 1083 |
| LMArena Russian | 1234 | 1169 |
| LMArena Spanish | 1228 | 1169 |
Instruction Following Qwen2-72B leads
Gemma 2 27B: 60.5 (#249), Qwen2-72B: 61.7 (#241)
| Benchmark | Gemma 2 27B | Qwen2-72B |
|---|---|---|
| LMArena Instruction Following | 1206 | 1181 |
| LiveBench Instruction Following | 58.1% | — |
Long Context Gemma 2 27B leads
Gemma 2 27B: 37.3 (#218), Qwen2-72B: 36.1 (#235)
| Benchmark | Gemma 2 27B | Qwen2-72B |
|---|---|---|
| LMArena Longer Query | 1231 | 1192 |
Writing & Preference Gemma 2 27B leads
Gemma 2 27B: 44.2 (#225), Qwen2-72B: 40.8 (#241)
| Benchmark | Gemma 2 27B | Qwen2-72B |
|---|---|---|
| LMArena Text | 1231 | 1203 |
| LMArena Creative Writing | 1241 | 1181 |
| LMArena Multi-Turn | 1224 | 1196 |
| LiveBench Language | 32.6% | — |
Frequently asked questions
Is Gemma 2 27B better than Qwen2-72B?
Gemma 2 27B and Qwen2-72B score almost the same on the Noometry Index (29.4 vs 30.0), so choose on price, context window or the category you care about most.
Is Gemma 2 27B or Qwen2-72B better for coding?
Gemma 2 27B scores higher on coding benchmarks: 34.1 versus 29.1 in the Noometry coding category.
How many benchmarks do Gemma 2 27B and Qwen2-72B share?
23 benchmarks have published results for both models. Gemma 2 27B has 34 scored results on Noometry and Qwen2-72B has 26.