Model comparison
Gemma 4 31B IT vs QwQ-32B
Gemma 4 31B IT is the stronger model overall, scoring 43.5 to 39.8 on the Noometry Index.
Last verified . 19 shared benchmarks.
Google
Alibaba (Qwen)Summary
- They share 19 benchmarks with published results for both. Gemma 4 31B IT scores higher in 7 categories and QwQ-32B in 1 category; 7 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Gemma 4 31B IT leads 60.5 to 50.6.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 73.3% for Gemma 4 31B IT and 59.2% for QwQ-32B.
Side by side
| Gemma 4 31B IT | QwQ-32B | |
|---|---|---|
| Provider | Alibaba (Qwen) | |
| Noometry Index | 43.5 | 39.8 |
| Released | 2026-04-02 | 2024-11-28 |
| Weights | Open | Open |
| Context window | 262K | — |
| Max output | 33K | — |
| Input $ / M tokens | $0.09 | — |
| Output $ / M tokens | $0.34 | — |
| Results tracked | 35 | 36 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Gemma 4 31B IT leads
Gemma 4 31B IT: 42.3 (#108), QwQ-32B: 35.4 (#226)
| Benchmark | Gemma 4 31B IT | QwQ-32B |
|---|---|---|
| LMArena Coding | 1459 | 1333 |
| Aider Polyglot | — | 20.9% |
| LMArena WebDev | 1366 | — |
| SciCode | 43.4% | — |
| WeirdML | 52.3% | — |
| BigCodeBench Instruct | — | 44.6% |
| LiveBench Coding | — | 72.2% |
| BigCodeBench Complete | — | 54.4% |
| ALE-Bench | 925.5 | — |
Reasoning Gemma 4 31B IT leads
Gemma 4 31B IT: 27.2 (#122), QwQ-32B: 23.7 (#174)
| Benchmark | Gemma 4 31B IT | QwQ-32B |
|---|---|---|
| Chess Puzzles | 5% | 5% |
| LMArena Hard Prompts | 1448 | 1325 |
| Epoch Capabilities Index | 142.74 | 137.6 |
| Kagi LLM Benchmark | 63.5% | — |
| NYT Connections (extended) | 70.6% | — |
| CritPt | 1.4% | — |
| Thematic Generalization | 53% | — |
| LiveBench Reasoning | — | 83.5% |
| DTBench | 82.7% | — |
| LiveBench Data Analysis | — | 65% |
| LMCA | 39.3% | — |
| Surface Evolver Bench | 30.6% | — |
| ForecastBench | — | 58.3 |
| LiveBench | — | 72% |
Math Gemma 4 31B IT leads
Gemma 4 31B IT: 43.2 (#81), QwQ-32B: 38.0 (#143)
| Benchmark | Gemma 4 31B IT | QwQ-32B |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 73.3% | 59.2% |
| LMArena Math | 1465 | 1359 |
| LiveBench Math | — | 77.8% |
Knowledge Too close to call
Gemma 4 31B IT: 37.9 (#151), QwQ-32B: 37.2 (#158)
| Benchmark | Gemma 4 31B IT | QwQ-32B |
|---|---|---|
| GPQA Diamond | 75.8% | 65.3% |
| LMArena Expert | 1465 | 1324 |
| SimpleQA Verified | 10.4% | — |
| Confabulations | — | 15.6% |
| Vectara Hallucination Rate | 7.4% | — |
Multimodal Not comparable
Gemma 4 31B IT: 41.6 (#34), QwQ-32B: —
| Benchmark | Gemma 4 31B IT | QwQ-32B |
|---|---|---|
| LMArena Vision | 1277 | — |
| LMArena Document | 1425 | — |
Multilingual Gemma 4 31B IT leads
Gemma 4 31B IT: 53.8 (#57), QwQ-32B: 44.8 (#176)
| Benchmark | Gemma 4 31B IT | QwQ-32B |
|---|---|---|
| LMArena Non-English | 1431 | 1305 |
| LMArena Chinese | 1476 | 1378 |
| LMArena French | 1435 | 1336 |
| LMArena Russian | 1460 | 1297 |
| LMArena Spanish | 1444 | 1354 |
| LMArena German | — | 1313 |
| LMArena Japanese | — | 1262 |
| LMArena Korean | — | 1279 |
Instruction Following Gemma 4 31B IT leads
Gemma 4 31B IT: 75.5 (#61), QwQ-32B: 72.6 (#137)
| Benchmark | Gemma 4 31B IT | QwQ-32B |
|---|---|---|
| LMArena Instruction Following | 1433 | 1297 |
| LiveBench Instruction Following | — | 81.8% |
Long Context QwQ-32B leads
Gemma 4 31B IT: 44.2 (#71), QwQ-32B: 49.0 (#11)
| Benchmark | Gemma 4 31B IT | QwQ-32B |
|---|---|---|
| LMArena Longer Query | 1446 | 1308 |
| Fiction.LiveBench | — | 83.3% |
Writing & Preference Gemma 4 31B IT leads
Gemma 4 31B IT: 60.5 (#96), QwQ-32B: 50.6 (#180)
| Benchmark | Gemma 4 31B IT | QwQ-32B |
|---|---|---|
| LMArena Text | 1443 | 1329 |
| LMArena Creative Writing | 1415 | 1288 |
| EQ-Bench Creative Writing | 1368 | 1257 |
| LMArena Multi-Turn | 1452 | 1314 |
| Short-Story Creative Writing | — | 80.2% |
| EQ-Bench 4 | 1120 | — |
| LiveBench Language | — | 51.4% |
Frequently asked questions
Is Gemma 4 31B IT better than QwQ-32B?
Gemma 4 31B IT is the stronger model overall, scoring 43.5 to 39.8 on the Noometry Index.
Is Gemma 4 31B IT or QwQ-32B better for coding?
Gemma 4 31B IT scores higher on coding benchmarks: 42.3 versus 35.4 in the Noometry coding category.
How many benchmarks do Gemma 4 31B IT and QwQ-32B share?
19 benchmarks have published results for both models. Gemma 4 31B IT has 35 scored results on Noometry and QwQ-32B has 36.