Model comparison
Llama 4 Maverick vs QwQ-32B
QwQ-32B is the stronger model overall, scoring 39.4 to 30.6 on the Noometry Index.
Last verified . 28 shared benchmarks.
Meta
Alibaba (Qwen)Summary
- They share 28 benchmarks with published results for both. Llama 4 Maverick scores higher in 0 categories and QwQ-32B in 8 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in long context, where QwQ-32B leads 49.0 to 31.4.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 20.6% for Llama 4 Maverick and 59.2% for QwQ-32B.
Side by side
| Llama 4 Maverick | QwQ-32B | |
|---|---|---|
| Provider | Meta | Alibaba (Qwen) |
| Noometry Index | 30.6 | 39.4 |
| Released | 2025-04-05 | 2024-11-28 |
| Weights | Open | Open |
| Context window | 128K | — |
| Max output | 4K | — |
| Input $ / M tokens | $0.19 | — |
| Output $ / M tokens | $0.65 | — |
| Results tracked | 54 | 36 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding QwQ-32B leads
Llama 4 Maverick: 26.3 (#318), QwQ-32B: 34.9 (#220)
| Benchmark | Llama 4 Maverick | QwQ-32B |
|---|---|---|
| Aider Polyglot | 15.6% | 20.9% |
| BigCodeBench Instruct | 49.7% | 44.6% |
| LMArena Coding | 1302 | 1333 |
| BigCodeBench Complete | 61.4% | 54.4% |
| SWE-bench Verified (bash only) | 21% | — |
| SciCode | 33.1% | — |
| WeirdML | 24.5% | — |
| LiveBench Coding | — | 72.2% |
| ALE-Bench | 172.97 | — |
Agentic & Tool Use Not comparable
Llama 4 Maverick: 27.9 (#86), QwQ-32B: —
| Benchmark | Llama 4 Maverick | QwQ-32B |
|---|---|---|
| Berkeley Function Calling Leaderboard | 37.3% | — |
Reasoning QwQ-32B leads
Llama 4 Maverick: 10.1 (#337), QwQ-32B: 22.9 (#171)
| Benchmark | Llama 4 Maverick | QwQ-32B |
|---|---|---|
| LMArena Hard Prompts | 1281 | 1326 |
| Epoch Capabilities Index | 132.2 | 137.6 |
| ForecastBench | 57.5 | 58.3 |
| ARC-AGI-2 | 0% | — |
| SimpleBench | 27.7% | — |
| Kagi LLM Benchmark | 55.9% | — |
| NYT Connections (extended) | 8% | — |
| ARC-AGI-1 | 4.4% | — |
| CritPt | 0% | — |
| Chess Puzzles | — | 5% |
| EnigmaEval | 0.6% | — |
| LiveBench Reasoning | — | 83.5% |
| DTBench | 61.9% | — |
| LiveBench Data Analysis | — | 65% |
| LMCA | 15.9% | — |
| LiveBench | — | 72% |
Math QwQ-32B leads
Llama 4 Maverick: 24.6 (#256), QwQ-32B: 36.2 (#123)
| Benchmark | Llama 4 Maverick | QwQ-32B |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 20.6% | 59.2% |
| LMArena Math | 1299 | 1359 |
| Omni-MATH | 42.2% | — |
| LiveBench Math | — | 77.8% |
| MATH Level 5 | 73% | — |
| FrontierMath (Feb 2025 set) | 0.7% | — |
Knowledge QwQ-32B leads
Llama 4 Maverick: 33.3 (#196), QwQ-32B: 37.2 (#150)
| Benchmark | Llama 4 Maverick | QwQ-32B |
|---|---|---|
| GPQA Diamond | 67% | 65.3% |
| Confabulations | 22.6% | 15.6% |
| LMArena Expert | 1259 | 1323 |
| Humanity's Last Exam | 5.7% | — |
| MMLU-Pro | 81% | — |
| Vectara Hallucination Rate | 8.2% | — |
| GPQA (HELM) | 65% | — |
Multimodal Not comparable
Llama 4 Maverick: 30.9 (#100), QwQ-32B: —
| Benchmark | Llama 4 Maverick | QwQ-32B |
|---|---|---|
| LMArena Vision | 1141 | — |
| GeoBench | 52% | — |
| SpatialViz-Bench | 31.8% | — |
Multilingual QwQ-32B leads
Llama 4 Maverick: 42.4 (#190), QwQ-32B: 45.0 (#171)
| Benchmark | Llama 4 Maverick | QwQ-32B |
|---|---|---|
| LMArena Non-English | 1269 | 1306 |
| LMArena Chinese | 1277 | 1378 |
| LMArena French | 1258 | 1337 |
| LMArena German | 1291 | 1313 |
| LMArena Japanese | 1207 | 1263 |
| LMArena Korean | 1203 | 1278 |
| LMArena Russian | 1286 | 1297 |
| LMArena Spanish | 1293 | 1353 |
Instruction Following Too close to call
Llama 4 Maverick: 71.9 (#140), QwQ-32B: 72.8 (#131)
| Benchmark | Llama 4 Maverick | QwQ-32B |
|---|---|---|
| LMArena Instruction Following | 1267 | 1297 |
| LiveBench Instruction Following | — | 81.8% |
| IFEval | 90.8% | — |
Long Context QwQ-32B leads
Llama 4 Maverick: 31.4 (#274), QwQ-32B: 49.0 (#11)
| Benchmark | Llama 4 Maverick | QwQ-32B |
|---|---|---|
| Fiction.LiveBench | 46.2% | 83.3% |
| LMArena Longer Query | 1280 | 1308 |
Writing & Preference QwQ-32B leads
Llama 4 Maverick: 39.0 (#247), QwQ-32B: 50.9 (#175)
| Benchmark | Llama 4 Maverick | QwQ-32B |
|---|---|---|
| LMArena Text | 1287 | 1329 |
| LMArena Creative Writing | 1266 | 1288 |
| Short-Story Creative Writing | 62% | 80.2% |
| EQ-Bench Creative Writing | 860 | 1257 |
| LMArena Multi-Turn | 1289 | 1314 |
| WildBench | 80% | — |
| LiveBench Language | — | 51.4% |
Frequently asked questions
Is Llama 4 Maverick better than QwQ-32B?
QwQ-32B is the stronger model overall, scoring 39.4 to 30.6 on the Noometry Index.
Is Llama 4 Maverick or QwQ-32B better for coding?
QwQ-32B scores higher on coding benchmarks: 34.9 versus 26.3 in the Noometry coding category.
How many benchmarks do Llama 4 Maverick and QwQ-32B share?
28 benchmarks have published results for both models. Llama 4 Maverick has 54 scored results on Noometry and QwQ-32B has 36.