Model comparison
Llama 4 Scout vs Qwen3.6 Max Preview
Qwen3.6 Max Preview is the stronger model overall, scoring 51.1 to 27.4 on the Noometry Index. Llama 4 Scout costs 19× less per token, which makes it the better buy when Qwen3.6 Max Preview's lead doesn't matter for your workload.
Last verified . 20 shared benchmarks.
Meta
Alibaba (Qwen)Summary
- They share 20 benchmarks with published results for both. Llama 4 Scout scores higher in 0 categories and Qwen3.6 Max Preview in 8 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in math, where Qwen3.6 Max Preview leads 52.2 to 18.4.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 7.8% for Llama 4 Scout and 91.1% for Qwen3.6 Max Preview.
- Llama 4 Scout is cheaper at $0.10 / $0.30 per million input/output tokens, against $1.30 / $7.80 for Qwen3.6 Max Preview.
- Qwen3.6 Max Preview accepts more context: 262K tokens versus 128K.
- Llama 4 Scout has downloadable open weights; the other is API-only.
Side by side
| Llama 4 Scout | Qwen3.6 Max Preview | |
|---|---|---|
| Provider | Meta | Alibaba (Qwen) |
| Noometry Index | 27.4 | 51.1 |
| Released | 2025-04-05 | 2026-04-20 |
| Weights | Open | Proprietary |
| Context window | 128K | 262K |
| Max output | 4K | 66K |
| Input $ / M tokens | $0.10 | $1.30 |
| Output $ / M tokens | $0.30 | $7.80 |
| Results tracked | 43 | 29 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Qwen3.6 Max Preview leads
Llama 4 Scout: 19.9 (#334), Qwen3.6 Max Preview: 48.6 (#50)
| Benchmark | Llama 4 Scout | Qwen3.6 Max Preview |
|---|---|---|
| LMArena Coding | 1286 | 1472 |
| SWE-bench Verified | — | 76.7% |
| SWE-bench Verified (bash only) | 9.1% | — |
| LMArena WebDev | — | 1482 |
| SciCode | 17% | — |
| BigCodeBench Complete | 43.1% | — |
Agentic & Tool Use Not comparable
Llama 4 Scout: 24.4 (#109), Qwen3.6 Max Preview: —
| Benchmark | Llama 4 Scout | Qwen3.6 Max Preview |
|---|---|---|
| Berkeley Function Calling Leaderboard | 28.1% | — |
| Vending-Bench 2 | — | 4,254 |
Reasoning Qwen3.6 Max Preview leads
Llama 4 Scout: 9.2 (#339), Qwen3.6 Max Preview: 40.8 (#47)
| Benchmark | Llama 4 Scout | Qwen3.6 Max Preview |
|---|---|---|
| LMArena Hard Prompts | 1266 | 1457 |
| DTBench | 57.9% | 87.2% |
| LMCA | 12% | 42.5% |
| Epoch Capabilities Index | 129.64 | 149.27 |
| ARC-AGI-2 | 0% | — |
| SimpleBench | — | 63% |
| Kagi LLM Benchmark | 36.9% | — |
| NYT Connections (extended) | — | 74.1% |
| ARC-AGI-1 | 0.5% | — |
| CritPt | 0% | — |
| Chess Puzzles | — | 20% |
| Mystery Game Puzzles | — | 19% |
| ForecastBench | 57.5 | — |
Math Qwen3.6 Max Preview leads
Llama 4 Scout: 18.4 (#280), Qwen3.6 Max Preview: 52.2 (#40)
| Benchmark | Llama 4 Scout | Qwen3.6 Max Preview |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 7.8% | 91.1% |
| LMArena Math | 1286 | 1465 |
| FrontierMath (Feb 2025 set) | 0% | 23.1% |
| Omni-MATH | 37.3% | — |
| MATH Level 5 | 62.3% | — |
| FrontierMath Tier 4 (v1) | — | 4.2% |
Knowledge Qwen3.6 Max Preview leads
Llama 4 Scout: 31.8 (#208), Qwen3.6 Max Preview: 57.6 (#35)
| Benchmark | Llama 4 Scout | Qwen3.6 Max Preview |
|---|---|---|
| GPQA Diamond | 51.8% | 87.4% |
| LMArena Expert | 1236 | 1476 |
| SimpleQA Verified | — | 52% |
| MMLU-Pro | 74.2% | — |
| Vectara Hallucination Rate | 7.7% | — |
| GPQA (HELM) | 50.7% | — |
Multimodal Not comparable
Llama 4 Scout: 31.6 (#98), Qwen3.6 Max Preview: —
| Benchmark | Llama 4 Scout | Qwen3.6 Max Preview |
|---|---|---|
| LMArena Vision | 1118 | — |
| SpatialViz-Bench | 34.2% | — |
Multilingual Qwen3.6 Max Preview leads
Llama 4 Scout: 41.3 (#207), Qwen3.6 Max Preview: 54.3 (#46)
| Benchmark | Llama 4 Scout | Qwen3.6 Max Preview |
|---|---|---|
| LMArena Non-English | 1253 | 1436 |
| LMArena Chinese | 1256 | 1487 |
| LMArena French | 1283 | 1449 |
| LMArena Russian | 1263 | 1444 |
| LMArena Spanish | 1277 | 1452 |
| LMArena German | 1274 | — |
| LMArena Japanese | 1209 | — |
| LMArena Korean | 1207 | — |
Instruction Following Qwen3.6 Max Preview leads
Llama 4 Scout: 66.0 (#212), Qwen3.6 Max Preview: 75.8 (#51)
| Benchmark | Llama 4 Scout | Qwen3.6 Max Preview |
|---|---|---|
| LMArena Instruction Following | 1248 | 1437 |
| IFEval | 81.8% | — |
Long Context Qwen3.6 Max Preview leads
Llama 4 Scout: 27.5 (#289), Qwen3.6 Max Preview: 44.6 (#59)
| Benchmark | Llama 4 Scout | Qwen3.6 Max Preview |
|---|---|---|
| LMArena Longer Query | 1265 | 1457 |
| Fiction.LiveBench | 36% | — |
Writing & Preference Qwen3.6 Max Preview leads
Llama 4 Scout: 37.1 (#256), Qwen3.6 Max Preview: 64.0 (#58)
| Benchmark | Llama 4 Scout | Qwen3.6 Max Preview |
|---|---|---|
| LMArena Text | 1279 | 1447 |
| LMArena Creative Writing | 1249 | 1435 |
| LMArena Multi-Turn | 1281 | 1456 |
| EQ-Bench Creative Writing | 783 | — |
| WildBench | 78% | — |
Frequently asked questions
Is Llama 4 Scout better than Qwen3.6 Max Preview?
Qwen3.6 Max Preview is the stronger model overall, scoring 51.1 to 27.4 on the Noometry Index. Llama 4 Scout costs 19× less per token, which makes it the better buy when Qwen3.6 Max Preview's lead doesn't matter for your workload.
Which is cheaper, Llama 4 Scout or Qwen3.6 Max Preview?
Llama 4 Scout is cheaper. It lists at $0.10 per million input tokens and $0.30 per million output tokens; Qwen3.6 Max Preview lists at $1.30 and $7.80.
Is Llama 4 Scout or Qwen3.6 Max Preview better for coding?
Qwen3.6 Max Preview scores higher on coding benchmarks: 48.6 versus 19.9 in the Noometry coding category.
Which has the bigger context window?
Qwen3.6 Max Preview does, with 262K tokens against 128K.
How many benchmarks do Llama 4 Scout and Qwen3.6 Max Preview share?
20 benchmarks have published results for both models. Llama 4 Scout has 43 scored results on Noometry and Qwen3.6 Max Preview has 29.