Model comparison
Llama 4 Scout vs Qwen2.5-Max
Qwen2.5-Max is the stronger model overall, scoring 40.7 to 27.7 on the Noometry Index.
Last verified . 18 shared benchmarks.
Meta
Alibaba (Qwen)Summary
- They share 18 benchmarks with published results for both. Llama 4 Scout scores higher in 0 categories and Qwen2.5-Max in 8 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in coding, where Qwen2.5-Max leads 41.8 to 20.2.
- Llama 4 Scout has downloadable open weights; the other is API-only.
Side by side
| Llama 4 Scout | Qwen2.5-Max | |
|---|---|---|
| Provider | Meta | Alibaba (Qwen) |
| Noometry Index | 27.7 | 40.7 |
| Released | 2025-04-05 | 2025-01-25 |
| Weights | Open | Proprietary |
| Context window | 128K | — |
| Max output | 4K | — |
| Input $ / M tokens | $0.10 | — |
| Output $ / M tokens | $0.30 | — |
| Results tracked | 43 | 27 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Qwen2.5-Max leads
Llama 4 Scout: 20.2 (#339), Qwen2.5-Max: 41.8 (#117)
| Benchmark | Llama 4 Scout | Qwen2.5-Max |
|---|---|---|
| LMArena Coding | 1286 | 1359 |
| SWE-bench Verified (bash only) | 9.1% | — |
| SciCode | 17% | — |
| LiveBench Coding | — | 64.4% |
| BigCodeBench Complete | 43.1% | — |
Agentic & Tool Use Not comparable
Llama 4 Scout: 24.6 (#119), Qwen2.5-Max: —
| Benchmark | Llama 4 Scout | Qwen2.5-Max |
|---|---|---|
| Berkeley Function Calling Leaderboard | 28.1% | — |
Reasoning Qwen2.5-Max leads
Llama 4 Scout: 9.1 (#345), Qwen2.5-Max: 25.6 (#147)
| Benchmark | Llama 4 Scout | Qwen2.5-Max |
|---|---|---|
| LMArena Hard Prompts | 1266 | 1360 |
| Epoch Capabilities Index | 129.64 | 132.53 |
| ARC-AGI-2 | 0% | — |
| Kagi LLM Benchmark | 36.9% | — |
| ARC-AGI-1 | 0.5% | — |
| CritPt | 0% | — |
| LiveBench Reasoning | — | 51.4% |
| DTBench | 57.9% | — |
| LiveBench Data Analysis | — | 67.9% |
| LMCA | 12% | — |
| ForecastBench | 57.5 | — |
| LiveBench | — | 62.3% |
Math Qwen2.5-Max leads
Llama 4 Scout: 19.6 (#286), Qwen2.5-Max: 36.9 (#162)
| Benchmark | Llama 4 Scout | Qwen2.5-Max |
|---|---|---|
| LMArena Math | 1287 | 1369 |
| OTIS Mock AIME 2024-2025 | 7.8% | — |
| Omni-MATH | 37.3% | — |
| LiveBench Math | — | 58.4% |
| MATH Level 5 | 62.3% | — |
| FrontierMath (Feb 2025 set) | 0% | — |
Knowledge Qwen2.5-Max leads
Llama 4 Scout: 31.9 (#217), Qwen2.5-Max: 35.3 (#186)
| Benchmark | Llama 4 Scout | Qwen2.5-Max |
|---|---|---|
| LMArena Expert | 1235 | 1337 |
| GPQA Diamond | 51.8% | — |
| MMLU-Pro | 74.2% | — |
| Confabulations | — | 21.8% |
| Vectara Hallucination Rate | 7.7% | — |
| GPQA (HELM) | 50.7% | — |
Multimodal Not comparable
Llama 4 Scout: 32.2 (#102), Qwen2.5-Max: —
| Benchmark | Llama 4 Scout | Qwen2.5-Max |
|---|---|---|
| LMArena Vision | 1118 | — |
| SpatialViz-Bench | 34.2% | — |
Multilingual Qwen2.5-Max leads
Llama 4 Scout: 41.0 (#212), Qwen2.5-Max: 48.1 (#146)
| Benchmark | Llama 4 Scout | Qwen2.5-Max |
|---|---|---|
| LMArena Non-English | 1252 | 1352 |
| LMArena Chinese | 1255 | 1382 |
| LMArena French | 1282 | 1396 |
| LMArena German | 1272 | 1350 |
| LMArena Japanese | 1206 | 1300 |
| LMArena Korean | 1207 | 1304 |
| LMArena Russian | 1263 | 1353 |
| LMArena Spanish | 1278 | 1377 |
Instruction Following Qwen2.5-Max leads
Llama 4 Scout: 65.8 (#217), Qwen2.5-Max: 71.3 (#152)
| Benchmark | Llama 4 Scout | Qwen2.5-Max |
|---|---|---|
| LMArena Instruction Following | 1248 | 1335 |
| LiveBench Instruction Following | — | 75.3% |
| IFEval | 81.8% | — |
Long Context Qwen2.5-Max leads
Llama 4 Scout: 27.5 (#294), Qwen2.5-Max: 41.4 (#142)
| Benchmark | Llama 4 Scout | Qwen2.5-Max |
|---|---|---|
| LMArena Longer Query | 1265 | 1358 |
| Fiction.LiveBench | 36% | — |
Writing & Preference Qwen2.5-Max leads
Llama 4 Scout: 37.0 (#261), Qwen2.5-Max: 55.4 (#146)
| Benchmark | Llama 4 Scout | Qwen2.5-Max |
|---|---|---|
| LMArena Text | 1279 | 1367 |
| LMArena Creative Writing | 1249 | 1339 |
| LMArena Multi-Turn | 1280 | 1364 |
| Short-Story Creative Writing | — | 72.9% |
| EQ-Bench Creative Writing | 783 | — |
| WildBench | 78% | — |
| LiveBench Language | — | 56.3% |
Frequently asked questions
Is Llama 4 Scout better than Qwen2.5-Max?
Qwen2.5-Max is the stronger model overall, scoring 40.7 to 27.7 on the Noometry Index.
Is Llama 4 Scout or Qwen2.5-Max better for coding?
Qwen2.5-Max scores higher on coding benchmarks: 41.8 versus 20.2 in the Noometry coding category.
How many benchmarks do Llama 4 Scout and Qwen2.5-Max share?
18 benchmarks have published results for both models. Llama 4 Scout has 43 scored results on Noometry and Qwen2.5-Max has 27.