Model comparison
Gemma 2 9B vs QwQ-32B
QwQ-32B is the stronger model overall, scoring 39.8 to 25.9 on the Noometry Index.
Last verified . 30 shared benchmarks.
Google
Alibaba (Qwen)Summary
- They share 30 benchmarks with published results for both. Gemma 2 9B 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 9.9.
- The biggest single-benchmark swing is LiveBench Reasoning: 15.2% for Gemma 2 9B and 83.5% for QwQ-32B.
Side by side
| Gemma 2 9B | QwQ-32B | |
|---|---|---|
| Provider | Alibaba (Qwen) | |
| Noometry Index | 25.9 | 39.8 |
| Released | 2024-06-24 | 2024-11-28 |
| Weights | Open | Open |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 35 | 36 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding QwQ-32B leads
Gemma 2 9B: 29.4 (#304), QwQ-32B: 35.4 (#226)
| Benchmark | Gemma 2 9B | QwQ-32B |
|---|---|---|
| BigCodeBench Instruct | 34.7% | 44.6% |
| LiveBench Coding | 22.5% | 72.2% |
| LMArena Coding | 1173 | 1333 |
| BigCodeBench Complete | 40.6% | 54.4% |
| Aider Polyglot | — | 20.9% |
Reasoning QwQ-32B leads
Gemma 2 9B: 15.9 (#309), QwQ-32B: 23.7 (#174)
| Benchmark | Gemma 2 9B | QwQ-32B |
|---|---|---|
| LiveBench Reasoning | 15.2% | 83.5% |
| LMArena Hard Prompts | 1171 | 1325 |
| LiveBench Data Analysis | 36.4% | 65% |
| Epoch Capabilities Index | 119.83 | 137.6 |
| LiveBench | 28.7% | 72% |
| Chess Puzzles | — | 5% |
| ForecastBench | — | 58.3 |
| PIQA | 83.7% | — |
Math QwQ-32B leads
Gemma 2 9B: 9.9 (#318), QwQ-32B: 38.0 (#143)
| Benchmark | Gemma 2 9B | QwQ-32B |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 0.6% | 59.2% |
| LiveBench Math | 19.8% | 77.8% |
| LMArena Math | 1183 | 1359 |
| MATH Level 5 | 21% | — |
| GSM8K | 84.9% | — |
Knowledge QwQ-32B leads
Gemma 2 9B: 9.7 (#305), QwQ-32B: 37.2 (#158)
| Benchmark | Gemma 2 9B | QwQ-32B |
|---|---|---|
| GPQA Diamond | 27.5% | 65.3% |
| LMArena Expert | 1147 | 1324 |
| Confabulations | — | 15.6% |
| BoolQ | 85.7% | — |
| MMLU | 72.1% | — |
Multilingual QwQ-32B leads
Gemma 2 9B: 36.6 (#238), QwQ-32B: 44.8 (#176)
| Benchmark | Gemma 2 9B | QwQ-32B |
|---|---|---|
| LMArena Non-English | 1188 | 1305 |
| LMArena Chinese | 1185 | 1378 |
| LMArena French | 1190 | 1336 |
| LMArena German | 1186 | 1313 |
| LMArena Japanese | 1144 | 1262 |
| LMArena Korean | 1137 | 1279 |
| LMArena Russian | 1200 | 1297 |
| LMArena Spanish | 1200 | 1354 |
Instruction Following QwQ-32B leads
Gemma 2 9B: 57.6 (#269), QwQ-32B: 72.6 (#137)
| Benchmark | Gemma 2 9B | QwQ-32B |
|---|---|---|
| LiveBench Instruction Following | 52.6% | 81.8% |
| LMArena Instruction Following | 1178 | 1297 |
Long Context QwQ-32B leads
Gemma 2 9B: 36.3 (#233), QwQ-32B: 49.0 (#11)
| Benchmark | Gemma 2 9B | QwQ-32B |
|---|---|---|
| LMArena Longer Query | 1197 | 1308 |
| Fiction.LiveBench | — | 83.3% |
Writing & Preference QwQ-32B leads
Gemma 2 9B: 32.1 (#281), QwQ-32B: 50.6 (#180)
| Benchmark | Gemma 2 9B | QwQ-32B |
|---|---|---|
| LMArena Text | 1207 | 1329 |
| LMArena Creative Writing | 1206 | 1288 |
| EQ-Bench Creative Writing | 841 | 1257 |
| LMArena Multi-Turn | 1193 | 1314 |
| LiveBench Language | 25.5% | 51.4% |
| Short-Story Creative Writing | — | 80.2% |
Frequently asked questions
Is Gemma 2 9B better than QwQ-32B?
QwQ-32B is the stronger model overall, scoring 39.8 to 25.9 on the Noometry Index.
Is Gemma 2 9B or QwQ-32B better for coding?
QwQ-32B scores higher on coding benchmarks: 35.4 versus 29.4 in the Noometry coding category.
How many benchmarks do Gemma 2 9B and QwQ-32B share?
30 benchmarks have published results for both models. Gemma 2 9B has 35 scored results on Noometry and QwQ-32B has 36.