Model comparison
Gemma 2B vs QwQ-32B
QwQ-32B is the stronger model overall, scoring 39.8 to 29.6 on the Noometry Index.
Last verified . 12 shared benchmarks.
Google
Alibaba (Qwen)Summary
- They share 12 benchmarks with published results for both. Gemma 2B scores higher in 0 categories and QwQ-32B in 7 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where QwQ-32B leads 50.6 to 24.0.
Side by side
| Gemma 2B | QwQ-32B | |
|---|---|---|
| Provider | Alibaba (Qwen) | |
| Noometry Index | 29.6 | 39.8 |
| Released | 2024-02-21 | 2024-11-28 |
| Weights | Open | Open |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 23 | 36 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding QwQ-32B leads
Gemma 2B: 29.4 (#305), QwQ-32B: 35.4 (#226)
| Benchmark | Gemma 2B | QwQ-32B |
|---|---|---|
| LMArena Coding | 1010 | 1333 |
| Aider Polyglot | — | 20.9% |
| BigCodeBench Instruct | — | 44.6% |
| LiveBench Coding | — | 72.2% |
| BigCodeBench Complete | — | 54.4% |
| HumanEval+ | 20.7% | — |
| MBPP+ | 34.1% | — |
Reasoning QwQ-32B leads
Gemma 2B: 18.8 (#275), QwQ-32B: 23.7 (#174)
| Benchmark | Gemma 2B | QwQ-32B |
|---|---|---|
| LMArena Hard Prompts | 989 | 1325 |
| Epoch Capabilities Index | 94.2 | 137.6 |
| Chess Puzzles | — | 5% |
| LiveBench Reasoning | — | 83.5% |
| LiveBench Data Analysis | — | 65% |
| BIG-Bench Hard | 35.2% | — |
| ForecastBench | — | 58.3 |
| HellaSwag | 71.4% | — |
| LiveBench | — | 72% |
| PIQA | 77.3% | — |
| WinoGrande | 65.4% | — |
Math QwQ-32B leads
Gemma 2B: 30.0 (#239), QwQ-32B: 38.0 (#143)
| Benchmark | Gemma 2B | QwQ-32B |
|---|---|---|
| LMArena Math | 1009 | 1359 |
| OTIS Mock AIME 2024-2025 | — | 59.2% |
| LiveBench Math | — | 77.8% |
| GSM8K | 17.7% | — |
Knowledge Not comparable
Gemma 2B: —, QwQ-32B: 37.2 (#158)
| Benchmark | Gemma 2B | QwQ-32B |
|---|---|---|
| GPQA Diamond | — | 65.3% |
| Confabulations | — | 15.6% |
| LMArena Expert | — | 1324 |
| ARC (AI2) Challenge | 42.1% | — |
| BoolQ | 69.4% | — |
| MMLU | 42.3% | — |
| TriviaQA | 53.2% | — |
Multilingual QwQ-32B leads
Gemma 2B: 23.0 (#294), QwQ-32B: 44.8 (#176)
| Benchmark | Gemma 2B | QwQ-32B |
|---|---|---|
| LMArena Non-English | 958 | 1305 |
| LMArena Chinese | 986 | 1378 |
| LMArena Russian | 937 | 1297 |
| LMArena French | — | 1336 |
| LMArena German | — | 1313 |
| LMArena Japanese | — | 1262 |
| LMArena Korean | — | 1279 |
| LMArena Spanish | — | 1354 |
Instruction Following QwQ-32B leads
Gemma 2B: 48.5 (#302), QwQ-32B: 72.6 (#137)
| Benchmark | Gemma 2B | QwQ-32B |
|---|---|---|
| LMArena Instruction Following | 970 | 1297 |
| LiveBench Instruction Following | — | 81.8% |
Long Context QwQ-32B leads
Gemma 2B: 29.9 (#291), QwQ-32B: 49.0 (#11)
| Benchmark | Gemma 2B | QwQ-32B |
|---|---|---|
| LMArena Longer Query | 981 | 1308 |
| Fiction.LiveBench | — | 83.3% |
Writing & Preference QwQ-32B leads
Gemma 2B: 24.0 (#308), QwQ-32B: 50.6 (#180)
| Benchmark | Gemma 2B | QwQ-32B |
|---|---|---|
| LMArena Text | 1002 | 1329 |
| LMArena Creative Writing | 987 | 1288 |
| LMArena Multi-Turn | 945 | 1314 |
| Short-Story Creative Writing | — | 80.2% |
| EQ-Bench Creative Writing | — | 1257 |
| LiveBench Language | — | 51.4% |
Frequently asked questions
Is Gemma 2B better than QwQ-32B?
QwQ-32B is the stronger model overall, scoring 39.8 to 29.6 on the Noometry Index.
Is Gemma 2B 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 2B and QwQ-32B share?
12 benchmarks have published results for both models. Gemma 2B has 23 scored results on Noometry and QwQ-32B has 36.