Model comparison
Llama 4 Maverick vs Qwen2-72B
Llama 4 Maverick and Qwen2-72B score almost the same on the Noometry Index (30.9 vs 30.0), so choose on price, context window or the category you care about most.
Last verified . 23 shared benchmarks.
Meta
Alibaba (Qwen)Summary
- They share 23 benchmarks with published results for both. Llama 4 Maverick scores higher in 4 categories and Qwen2-72B in 5 categories; 9 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where Qwen2-72B leads 23.2 to 10.1.
- The biggest single-benchmark swing is MATH Level 5: 73% for Llama 4 Maverick and 39.1% for Qwen2-72B.
Side by side
| Llama 4 Maverick | Qwen2-72B | |
|---|---|---|
| Provider | Meta | Alibaba (Qwen) |
| Noometry Index | 30.9 | 30.0 |
| Released | 2025-04-05 | 2024-06-07 |
| Weights | Open | Open |
| Context window | 128K | — |
| Max output | 4K | — |
| Input $ / M tokens | $0.19 | — |
| Output $ / M tokens | $0.65 | — |
| Results tracked | 54 | 26 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Qwen2-72B leads
Llama 4 Maverick: 26.6 (#324), Qwen2-72B: 29.1 (#310)
| Benchmark | Llama 4 Maverick | Qwen2-72B |
|---|---|---|
| WeirdML | 24.5% | 11.3% |
| BigCodeBench Instruct | 49.7% | 38.5% |
| LMArena Coding | 1302 | 1196 |
| BigCodeBench Complete | 61.4% | 54% |
| SWE-bench Verified (bash only) | 21% | — |
| Aider Polyglot | 15.6% | — |
| SciCode | 33.1% | — |
| ALE-Bench | 172.97 | — |
Agentic & Tool Use Llama 4 Maverick leads
Llama 4 Maverick: 28.2 (#91), Qwen2-72B: 17.0 (#146)
| Benchmark | Llama 4 Maverick | Qwen2-72B |
|---|---|---|
| Berkeley Function Calling Leaderboard | 37.3% | — |
| TheAgentCompany | — | 1.1% |
| METR Time Horizons | — | 29.9% |
Reasoning Qwen2-72B leads
Llama 4 Maverick: 10.1 (#342), Qwen2-72B: 23.2 (#181)
| Benchmark | Llama 4 Maverick | Qwen2-72B |
|---|---|---|
| LMArena Hard Prompts | 1281 | 1191 |
| Epoch Capabilities Index | 132.2 | 125.28 |
| 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% | — |
| ForecastBench | 57.5 | — |
Math Qwen2-72B leads
Llama 4 Maverick: 26.0 (#262), Qwen2-72B: 30.2 (#236)
| Benchmark | Llama 4 Maverick | Qwen2-72B |
|---|---|---|
| LMArena Math | 1299 | 1235 |
| MATH Level 5 | 73% | 39.1% |
| OTIS Mock AIME 2024-2025 | 20.6% | — |
| Omni-MATH | 42.2% | — |
| FrontierMath (Feb 2025 set) | 0.7% | — |
Knowledge Llama 4 Maverick leads
Llama 4 Maverick: 33.4 (#204), Qwen2-72B: 21.2 (#275)
| Benchmark | Llama 4 Maverick | Qwen2-72B |
|---|---|---|
| GPQA Diamond | 67% | 40.8% |
| LMArena Expert | 1259 | 1171 |
| Humanity's Last Exam | 5.7% | — |
| MMLU-Pro | 81% | — |
| Confabulations | 22.6% | — |
| Vectara Hallucination Rate | 8.2% | — |
| GPQA (HELM) | 65% | — |
| MMLU | — | 82.4% |
Multimodal Not comparable
Llama 4 Maverick: 31.6 (#105), Qwen2-72B: —
| Benchmark | Llama 4 Maverick | Qwen2-72B |
|---|---|---|
| LMArena Vision | 1142 | — |
| GeoBench | 52% | — |
| SpatialViz-Bench | 31.8% | — |
Multilingual Llama 4 Maverick leads
Llama 4 Maverick: 42.2 (#195), Qwen2-72B: 35.9 (#244)
| Benchmark | Llama 4 Maverick | Qwen2-72B |
|---|---|---|
| LMArena Non-English | 1269 | 1176 |
| LMArena Chinese | 1277 | 1240 |
| LMArena French | 1259 | 1170 |
| LMArena German | 1291 | 1151 |
| LMArena Japanese | 1207 | 1111 |
| LMArena Korean | 1203 | 1083 |
| LMArena Russian | 1286 | 1169 |
| LMArena Spanish | 1293 | 1169 |
Instruction Following Llama 4 Maverick leads
Llama 4 Maverick: 71.7 (#146), Qwen2-72B: 61.7 (#241)
| Benchmark | Llama 4 Maverick | Qwen2-72B |
|---|---|---|
| LMArena Instruction Following | 1267 | 1181 |
| IFEval | 90.8% | — |
Long Context Qwen2-72B leads
Llama 4 Maverick: 31.4 (#279), Qwen2-72B: 36.1 (#235)
| Benchmark | Llama 4 Maverick | Qwen2-72B |
|---|---|---|
| LMArena Longer Query | 1280 | 1192 |
| Fiction.LiveBench | 46.2% | — |
Writing & Preference Qwen2-72B leads
Llama 4 Maverick: 38.8 (#252), Qwen2-72B: 40.8 (#241)
| Benchmark | Llama 4 Maverick | Qwen2-72B |
|---|---|---|
| LMArena Text | 1287 | 1203 |
| LMArena Creative Writing | 1267 | 1181 |
| LMArena Multi-Turn | 1289 | 1196 |
| Short-Story Creative Writing | 62% | — |
| EQ-Bench Creative Writing | 860 | — |
| WildBench | 80% | — |
Frequently asked questions
Is Llama 4 Maverick better than Qwen2-72B?
Llama 4 Maverick and Qwen2-72B score almost the same on the Noometry Index (30.9 vs 30.0), so choose on price, context window or the category you care about most.
Is Llama 4 Maverick or Qwen2-72B better for coding?
Qwen2-72B scores higher on coding benchmarks: 29.1 versus 26.6 in the Noometry coding category.
How many benchmarks do Llama 4 Maverick and Qwen2-72B share?
23 benchmarks have published results for both models. Llama 4 Maverick has 54 scored results on Noometry and Qwen2-72B has 26.