Model comparison
Gemma 2 27B vs QwQ-32B
QwQ-32B is the stronger model overall, scoring 39.8 to 29.4 on the Noometry Index.
Last verified . 30 shared benchmarks.
Google
Alibaba (Qwen)Summary
- They share 30 benchmarks with published results for both. Gemma 2 27B scores higher in 0 categories and QwQ-32B in 8 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in math, where QwQ-32B leads 38.0 to 10.7.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 1.4% for Gemma 2 27B and 59.2% for QwQ-32B.
Side by side
| Gemma 2 27B | QwQ-32B | |
|---|---|---|
| Provider | Alibaba (Qwen) | |
| Noometry Index | 29.4 | 39.8 |
| Released | 2024-06-24 | 2024-11-28 |
| Weights | Open | Open |
| Context window | 8K | — |
| Max output | 2K | — |
| Input $ / M tokens | $0.65 | — |
| Output $ / M tokens | $0.65 | — |
| Results tracked | 34 | 36 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding QwQ-32B leads
Gemma 2 27B: 34.1 (#246), QwQ-32B: 35.4 (#226)
| Benchmark | Gemma 2 27B | QwQ-32B |
|---|---|---|
| BigCodeBench Instruct | 42.8% | 44.6% |
| LiveBench Coding | 36% | 72.2% |
| LMArena Coding | 1211 | 1333 |
| BigCodeBench Complete | 52.5% | 54.4% |
| Aider Polyglot | — | 20.9% |
Reasoning QwQ-32B leads
Gemma 2 27B: 15.3 (#315), QwQ-32B: 23.7 (#174)
| Benchmark | Gemma 2 27B | QwQ-32B |
|---|---|---|
| LiveBench Reasoning | 28.1% | 83.5% |
| LMArena Hard Prompts | 1198 | 1325 |
| LiveBench Data Analysis | 47.9% | 65% |
| Epoch Capabilities Index | 122.08 | 137.6 |
| LiveBench | 38.2% | 72% |
| Chess Puzzles | — | 5% |
| DTBench | 48% | — |
| LMCA | 7.1% | — |
| ForecastBench | — | 58.3 |
Math QwQ-32B leads
Gemma 2 27B: 10.7 (#311), QwQ-32B: 38.0 (#143)
| Benchmark | Gemma 2 27B | QwQ-32B |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 1.4% | 59.2% |
| LiveBench Math | 26.5% | 77.8% |
| LMArena Math | 1212 | 1359 |
| MATH Level 5 | 27.9% | — |
Knowledge QwQ-32B leads
Gemma 2 27B: 19.0 (#280), QwQ-32B: 37.2 (#158)
| Benchmark | Gemma 2 27B | QwQ-32B |
|---|---|---|
| GPQA Diamond | 36.5% | 65.3% |
| Confabulations | 27.1% | 15.6% |
| LMArena Expert | 1172 | 1324 |
| MMLU | 75.7% | — |
Multilingual QwQ-32B leads
Gemma 2 27B: 38.6 (#226), QwQ-32B: 44.8 (#176)
| Benchmark | Gemma 2 27B | QwQ-32B |
|---|---|---|
| LMArena Non-English | 1217 | 1305 |
| LMArena Chinese | 1221 | 1378 |
| LMArena French | 1247 | 1336 |
| LMArena German | 1209 | 1313 |
| LMArena Japanese | 1175 | 1262 |
| LMArena Korean | 1174 | 1279 |
| LMArena Russian | 1234 | 1297 |
| LMArena Spanish | 1228 | 1354 |
Instruction Following QwQ-32B leads
Gemma 2 27B: 60.5 (#249), QwQ-32B: 72.6 (#137)
| Benchmark | Gemma 2 27B | QwQ-32B |
|---|---|---|
| LiveBench Instruction Following | 58.1% | 81.8% |
| LMArena Instruction Following | 1206 | 1297 |
Long Context QwQ-32B leads
Gemma 2 27B: 37.3 (#218), QwQ-32B: 49.0 (#11)
| Benchmark | Gemma 2 27B | QwQ-32B |
|---|---|---|
| LMArena Longer Query | 1231 | 1308 |
| Fiction.LiveBench | — | 83.3% |
Writing & Preference QwQ-32B leads
Gemma 2 27B: 44.2 (#225), QwQ-32B: 50.6 (#180)
| Benchmark | Gemma 2 27B | QwQ-32B |
|---|---|---|
| LMArena Text | 1231 | 1329 |
| LMArena Creative Writing | 1241 | 1288 |
| LMArena Multi-Turn | 1224 | 1314 |
| LiveBench Language | 32.6% | 51.4% |
| Short-Story Creative Writing | — | 80.2% |
| EQ-Bench Creative Writing | — | 1257 |
Frequently asked questions
Is Gemma 2 27B better than QwQ-32B?
QwQ-32B is the stronger model overall, scoring 39.8 to 29.4 on the Noometry Index.
Is Gemma 2 27B or QwQ-32B better for coding?
QwQ-32B scores higher on coding benchmarks: 35.4 versus 34.1 in the Noometry coding category.
How many benchmarks do Gemma 2 27B and QwQ-32B share?
30 benchmarks have published results for both models. Gemma 2 27B has 34 scored results on Noometry and QwQ-32B has 36.