Model comparison
Llama 4 Scout vs Qwen2-72B
Qwen2-72B is the stronger model overall, scoring 29.5 to 27.4 on the Noometry Index.
Last verified . 21 shared benchmarks.
Meta
Alibaba (Qwen)Summary
- They share 21 benchmarks with published results for both. Llama 4 Scout 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 22.2 to 9.2.
- The biggest single-benchmark swing is MATH Level 5: 62.3% for Llama 4 Scout and 39.1% for Qwen2-72B.
Side by side
| Llama 4 Scout | Qwen2-72B | |
|---|---|---|
| Provider | Meta | Alibaba (Qwen) |
| Noometry Index | 27.4 | 29.5 |
| Released | 2025-04-05 | 2024-06-07 |
| Weights | Open | Open |
| Context window | 128K | — |
| Max output | 4K | — |
| Input $ / M tokens | $0.10 | — |
| Output $ / M tokens | $0.30 | — |
| Results tracked | 43 | 26 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Qwen2-72B leads
Llama 4 Scout: 19.9 (#334), Qwen2-72B: 28.7 (#303)
| Benchmark | Llama 4 Scout | Qwen2-72B |
|---|---|---|
| LMArena Coding | 1286 | 1196 |
| BigCodeBench Complete | 43.1% | 54% |
| SWE-bench Verified (bash only) | 9.1% | — |
| SciCode | 17% | — |
| WeirdML | — | 11.3% |
| BigCodeBench Instruct | — | 38.5% |
Agentic & Tool Use Llama 4 Scout leads
Llama 4 Scout: 24.4 (#109), Qwen2-72B: 16.9 (#138)
| Benchmark | Llama 4 Scout | Qwen2-72B |
|---|---|---|
| Berkeley Function Calling Leaderboard | 28.1% | — |
| TheAgentCompany | — | 1.1% |
| METR Time Horizons | — | 29.9% |
Reasoning Qwen2-72B leads
Llama 4 Scout: 9.2 (#339), Qwen2-72B: 22.2 (#184)
| Benchmark | Llama 4 Scout | Qwen2-72B |
|---|---|---|
| LMArena Hard Prompts | 1266 | 1191 |
| Epoch Capabilities Index | 129.64 | 125.27 |
| ARC-AGI-2 | 0% | — |
| Kagi LLM Benchmark | 36.9% | — |
| ARC-AGI-1 | 0.5% | — |
| CritPt | 0% | — |
| DTBench | 57.9% | — |
| LMCA | 12% | — |
| ForecastBench | 57.5 | — |
Math Qwen2-72B leads
Llama 4 Scout: 18.4 (#280), Qwen2-72B: 27.9 (#232)
| Benchmark | Llama 4 Scout | Qwen2-72B |
|---|---|---|
| LMArena Math | 1286 | 1235 |
| MATH Level 5 | 62.3% | 39.1% |
| OTIS Mock AIME 2024-2025 | 7.8% | — |
| Omni-MATH | 37.3% | — |
| FrontierMath (Feb 2025 set) | 0% | — |
Knowledge Llama 4 Scout leads
Llama 4 Scout: 31.8 (#208), Qwen2-72B: 21.2 (#270)
| Benchmark | Llama 4 Scout | Qwen2-72B |
|---|---|---|
| GPQA Diamond | 51.8% | 40.8% |
| LMArena Expert | 1236 | 1171 |
| MMLU-Pro | 74.2% | — |
| Vectara Hallucination Rate | 7.7% | — |
| GPQA (HELM) | 50.7% | — |
| MMLU | — | 82.4% |
Multimodal Not comparable
Llama 4 Scout: 31.6 (#98), Qwen2-72B: —
| Benchmark | Llama 4 Scout | Qwen2-72B |
|---|---|---|
| LMArena Vision | 1118 | — |
| SpatialViz-Bench | 34.2% | — |
Multilingual Llama 4 Scout leads
Llama 4 Scout: 41.3 (#207), Qwen2-72B: 36.0 (#239)
| Benchmark | Llama 4 Scout | Qwen2-72B |
|---|---|---|
| LMArena Non-English | 1253 | 1176 |
| LMArena Chinese | 1256 | 1240 |
| LMArena French | 1283 | 1169 |
| LMArena German | 1274 | 1151 |
| LMArena Japanese | 1209 | 1111 |
| LMArena Korean | 1207 | 1083 |
| LMArena Russian | 1263 | 1169 |
| LMArena Spanish | 1277 | 1168 |
Instruction Following Llama 4 Scout leads
Llama 4 Scout: 66.0 (#212), Qwen2-72B: 62.0 (#236)
| Benchmark | Llama 4 Scout | Qwen2-72B |
|---|---|---|
| LMArena Instruction Following | 1248 | 1181 |
| IFEval | 81.8% | — |
Long Context Qwen2-72B leads
Llama 4 Scout: 27.5 (#289), Qwen2-72B: 36.1 (#230)
| Benchmark | Llama 4 Scout | Qwen2-72B |
|---|---|---|
| LMArena Longer Query | 1265 | 1193 |
| Fiction.LiveBench | 36% | — |
Writing & Preference Qwen2-72B leads
Llama 4 Scout: 37.1 (#256), Qwen2-72B: 41.0 (#236)
| Benchmark | Llama 4 Scout | Qwen2-72B |
|---|---|---|
| LMArena Text | 1279 | 1203 |
| LMArena Creative Writing | 1249 | 1181 |
| LMArena Multi-Turn | 1281 | 1195 |
| EQ-Bench Creative Writing | 783 | — |
| WildBench | 78% | — |
Frequently asked questions
Is Llama 4 Scout better than Qwen2-72B?
Qwen2-72B is the stronger model overall, scoring 29.5 to 27.4 on the Noometry Index.
Is Llama 4 Scout or Qwen2-72B better for coding?
Qwen2-72B scores higher on coding benchmarks: 28.7 versus 19.9 in the Noometry coding category.
How many benchmarks do Llama 4 Scout and Qwen2-72B share?
21 benchmarks have published results for both models. Llama 4 Scout has 43 scored results on Noometry and Qwen2-72B has 26.