Model comparison
Llama 4 Maverick vs Qwen1.5-32B
Llama 4 Maverick and Qwen1.5-32B score almost the same on the Noometry Index (30.6 vs 30.0), so choose on price, context window or the category you care about most.
Last verified . 20 shared benchmarks.
Meta
Alibaba (Qwen)Summary
- They share 20 benchmarks with published results for both. Llama 4 Maverick scores higher in 4 categories and Qwen1.5-32B in 4 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Llama 4 Maverick leads 33.3 to 13.5.
- The biggest single-benchmark swing is GPQA Diamond: 67% for Llama 4 Maverick and 30.7% for Qwen1.5-32B.
Side by side
| Llama 4 Maverick | Qwen1.5-32B | |
|---|---|---|
| Provider | Meta | Alibaba (Qwen) |
| Noometry Index | 30.6 | 30.0 |
| Released | 2025-04-05 | 2024-02-04 |
| Weights | Open | Open |
| Context window | 128K | — |
| Max output | 4K | — |
| Input $ / M tokens | $0.19 | — |
| Output $ / M tokens | $0.65 | — |
| Results tracked | 54 | 21 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Qwen1.5-32B leads
Llama 4 Maverick: 26.3 (#318), Qwen1.5-32B: 31.1 (#278)
| Benchmark | Llama 4 Maverick | Qwen1.5-32B |
|---|---|---|
| BigCodeBench Instruct | 49.7% | 32.3% |
| LMArena Coding | 1302 | 1155 |
| BigCodeBench Complete | 61.4% | 42% |
| SWE-bench Verified (bash only) | 21% | — |
| Aider Polyglot | 15.6% | — |
| SciCode | 33.1% | — |
| WeirdML | 24.5% | — |
| ALE-Bench | 172.97 | — |
Agentic & Tool Use Not comparable
Llama 4 Maverick: 27.9 (#86), Qwen1.5-32B: —
| Benchmark | Llama 4 Maverick | Qwen1.5-32B |
|---|---|---|
| Berkeley Function Calling Leaderboard | 37.3% | — |
Reasoning Qwen1.5-32B leads
Llama 4 Maverick: 10.1 (#337), Qwen1.5-32B: 20.9 (#210)
| Benchmark | Llama 4 Maverick | Qwen1.5-32B |
|---|---|---|
| LMArena Hard Prompts | 1281 | 1131 |
| ARC-AGI-2 | 0% | — |
| SimpleBench | 27.7% | — |
| Kagi LLM Benchmark | 55.9% | — |
| NYT Connections (extended) | 8% | — |
| ARC-AGI-1 | 4.4% | — |
| CritPt | 0% | — |
| EnigmaEval | 0.6% | — |
| DTBench | 61.9% | — |
| LMCA | 15.9% | — |
| Epoch Capabilities Index | 132.2 | — |
| ForecastBench | 57.5 | — |
Math Qwen1.5-32B leads
Llama 4 Maverick: 24.6 (#256), Qwen1.5-32B: 30.5 (#207)
| Benchmark | Llama 4 Maverick | Qwen1.5-32B |
|---|---|---|
| LMArena Math | 1299 | 1155 |
| OTIS Mock AIME 2024-2025 | 20.6% | — |
| Omni-MATH | 42.2% | — |
| MATH Level 5 | 73% | — |
| FrontierMath (Feb 2025 set) | 0.7% | — |
Knowledge Llama 4 Maverick leads
Llama 4 Maverick: 33.3 (#196), Qwen1.5-32B: 13.5 (#291)
| Benchmark | Llama 4 Maverick | Qwen1.5-32B |
|---|---|---|
| GPQA Diamond | 67% | 30.7% |
| LMArena Expert | 1259 | 1126 |
| Humanity's Last Exam | 5.7% | — |
| MMLU-Pro | 81% | — |
| Confabulations | 22.6% | — |
| Vectara Hallucination Rate | 8.2% | — |
| GPQA (HELM) | 65% | — |
| MMLU | — | 74.4% |
Multimodal Not comparable
Llama 4 Maverick: 30.9 (#100), Qwen1.5-32B: —
| Benchmark | Llama 4 Maverick | Qwen1.5-32B |
|---|---|---|
| LMArena Vision | 1141 | — |
| GeoBench | 52% | — |
| SpatialViz-Bench | 31.8% | — |
Multilingual Llama 4 Maverick leads
Llama 4 Maverick: 42.4 (#190), Qwen1.5-32B: 31.6 (#254)
| Benchmark | Llama 4 Maverick | Qwen1.5-32B |
|---|---|---|
| LMArena Non-English | 1269 | 1106 |
| LMArena Chinese | 1277 | 1176 |
| LMArena French | 1258 | 1100 |
| LMArena German | 1291 | 1058 |
| LMArena Japanese | 1207 | 1027 |
| LMArena Korean | 1203 | 1007 |
| LMArena Russian | 1286 | 1073 |
| LMArena Spanish | 1293 | 1089 |
Instruction Following Llama 4 Maverick leads
Llama 4 Maverick: 71.9 (#140), Qwen1.5-32B: 58.0 (#260)
| Benchmark | Llama 4 Maverick | Qwen1.5-32B |
|---|---|---|
| LMArena Instruction Following | 1267 | 1116 |
| IFEval | 90.8% | — |
Long Context Qwen1.5-32B leads
Llama 4 Maverick: 31.4 (#274), Qwen1.5-32B: 34.7 (#241)
| Benchmark | Llama 4 Maverick | Qwen1.5-32B |
|---|---|---|
| LMArena Longer Query | 1280 | 1146 |
| Fiction.LiveBench | 46.2% | — |
Writing & Preference Llama 4 Maverick leads
Llama 4 Maverick: 39.0 (#247), Qwen1.5-32B: 34.4 (#266)
| Benchmark | Llama 4 Maverick | Qwen1.5-32B |
|---|---|---|
| LMArena Text | 1287 | 1137 |
| LMArena Creative Writing | 1266 | 1083 |
| LMArena Multi-Turn | 1289 | 1140 |
| Short-Story Creative Writing | 62% | — |
| EQ-Bench Creative Writing | 860 | — |
| WildBench | 80% | — |
Frequently asked questions
Is Llama 4 Maverick better than Qwen1.5-32B?
Llama 4 Maverick and Qwen1.5-32B score almost the same on the Noometry Index (30.6 vs 30.0), so choose on price, context window or the category you care about most.
Is Llama 4 Maverick or Qwen1.5-32B better for coding?
Qwen1.5-32B scores higher on coding benchmarks: 31.1 versus 26.3 in the Noometry coding category.
How many benchmarks do Llama 4 Maverick and Qwen1.5-32B share?
20 benchmarks have published results for both models. Llama 4 Maverick has 54 scored results on Noometry and Qwen1.5-32B has 21.