Model comparison
Llama 4 Scout vs Qwen Max
Qwen Max is the stronger model overall, scoring 34.7 to 27.7 on the Noometry Index. Llama 4 Scout costs 19× less per token, which makes it the better buy when Qwen Max's lead doesn't matter for your workload.
Last verified . 22 shared benchmarks.
Meta
Alibaba (Qwen)Summary
- They share 22 benchmarks with published results for both. Llama 4 Scout scores higher in 1 category and Qwen Max in 7 categories; 6 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where Qwen Max leads 25.1 to 9.1.
- The biggest single-benchmark swing is Fiction.LiveBench: 36% for Llama 4 Scout and 66.7% for Qwen Max.
- Llama 4 Scout is cheaper at $0.10 / $0.30 per million input/output tokens, against $1.60 / $6.40 for Qwen Max.
- Llama 4 Scout accepts more context: 128K tokens versus 33K.
- Llama 4 Scout has downloadable open weights; the other is API-only.
Side by side
| Llama 4 Scout | Qwen Max | |
|---|---|---|
| Provider | Meta | Alibaba (Qwen) |
| Noometry Index | 27.7 | 34.7 |
| Released | 2025-04-05 | 2024-04-03 |
| Weights | Open | Proprietary |
| Context window | 128K | 33K |
| Max output | 4K | 8K |
| Input $ / M tokens | $0.10 | $1.60 |
| Output $ / M tokens | $0.30 | $6.40 |
| Results tracked | 43 | 23 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Qwen Max leads
Llama 4 Scout: 20.2 (#339), Qwen Max: 30.7 (#292)
| Benchmark | Llama 4 Scout | Qwen Max |
|---|---|---|
| LMArena Coding | 1286 | 1288 |
| SWE-bench Verified (bash only) | 9.1% | — |
| Aider Polyglot | — | 21.8% |
| SciCode | 17% | — |
| BigCodeBench Complete | 43.1% | — |
Agentic & Tool Use Not comparable
Llama 4 Scout: 24.6 (#119), Qwen Max: —
| Benchmark | Llama 4 Scout | Qwen Max |
|---|---|---|
| Berkeley Function Calling Leaderboard | 28.1% | — |
Reasoning Qwen Max leads
Llama 4 Scout: 9.1 (#345), Qwen Max: 25.1 (#151)
| Benchmark | Llama 4 Scout | Qwen Max |
|---|---|---|
| LMArena Hard Prompts | 1266 | 1269 |
| ARC-AGI-2 | 0% | — |
| Kagi LLM Benchmark | 36.9% | — |
| ARC-AGI-1 | 0.5% | — |
| CritPt | 0% | — |
| DTBench | 57.9% | — |
| LMCA | 12% | — |
| Epoch Capabilities Index | 129.64 | — |
| ForecastBench | 57.5 | — |
Math Qwen Max leads
Llama 4 Scout: 19.6 (#286), Qwen Max: 22.3 (#276)
| Benchmark | Llama 4 Scout | Qwen Max |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 7.8% | 16.1% |
| LMArena Math | 1287 | 1275 |
| MATH Level 5 | 62.3% | 67.2% |
| FrontierMath (Feb 2025 set) | 0% | 1% |
| Omni-MATH | 37.3% | — |
Knowledge Llama 4 Scout leads
Llama 4 Scout: 31.9 (#217), Qwen Max: 30.3 (#228)
| Benchmark | Llama 4 Scout | Qwen Max |
|---|---|---|
| GPQA Diamond | 51.8% | 56.1% |
| LMArena Expert | 1235 | 1248 |
| MMLU-Pro | 74.2% | — |
| Vectara Hallucination Rate | 7.7% | — |
| GPQA (HELM) | 50.7% | — |
Multimodal Not comparable
Llama 4 Scout: 32.2 (#102), Qwen Max: —
| Benchmark | Llama 4 Scout | Qwen Max |
|---|---|---|
| LMArena Vision | 1118 | — |
| SpatialViz-Bench | 34.2% | — |
Multilingual Too close to call
Llama 4 Scout: 41.0 (#212), Qwen Max: 41.8 (#202)
| Benchmark | Llama 4 Scout | Qwen Max |
|---|---|---|
| LMArena Non-English | 1252 | 1263 |
| LMArena Chinese | 1255 | 1254 |
| LMArena French | 1282 | 1330 |
| LMArena German | 1272 | 1254 |
| LMArena Japanese | 1206 | 1205 |
| LMArena Korean | 1207 | 1142 |
| LMArena Russian | 1263 | 1274 |
| LMArena Spanish | 1278 | 1290 |
Instruction Following Too close to call
Llama 4 Scout: 65.8 (#217), Qwen Max: 66.5 (#208)
| Benchmark | Llama 4 Scout | Qwen Max |
|---|---|---|
| LMArena Instruction Following | 1248 | 1262 |
| IFEval | 81.8% | — |
Long Context Qwen Max leads
Llama 4 Scout: 27.5 (#294), Qwen Max: 39.4 (#180)
| Benchmark | Llama 4 Scout | Qwen Max |
|---|---|---|
| Fiction.LiveBench | 36% | 66.7% |
| LMArena Longer Query | 1265 | 1288 |
Writing & Preference Qwen Max leads
Llama 4 Scout: 37.0 (#261), Qwen Max: 47.8 (#205)
| Benchmark | Llama 4 Scout | Qwen Max |
|---|---|---|
| LMArena Text | 1279 | 1282 |
| LMArena Creative Writing | 1249 | 1248 |
| LMArena Multi-Turn | 1280 | 1277 |
| EQ-Bench Creative Writing | 783 | — |
| WildBench | 78% | — |
Frequently asked questions
Is Llama 4 Scout better than Qwen Max?
Qwen Max is the stronger model overall, scoring 34.7 to 27.7 on the Noometry Index. Llama 4 Scout costs 19× less per token, which makes it the better buy when Qwen Max's lead doesn't matter for your workload.
Which is cheaper, Llama 4 Scout or Qwen Max?
Llama 4 Scout is cheaper. It lists at $0.10 per million input tokens and $0.30 per million output tokens; Qwen Max lists at $1.60 and $6.40.
Is Llama 4 Scout or Qwen Max better for coding?
Qwen Max scores higher on coding benchmarks: 30.7 versus 20.2 in the Noometry coding category.
Which has the bigger context window?
Llama 4 Scout does, with 128K tokens against 33K.
How many benchmarks do Llama 4 Scout and Qwen Max share?
22 benchmarks have published results for both models. Llama 4 Scout has 43 scored results on Noometry and Qwen Max has 23.