Model comparison
Llama 4 Scout vs Qwen3.7 Max
Qwen3.7 Max is the stronger model overall, scoring 51.4 to 27.4 on the Noometry Index. Llama 4 Scout costs 25× less per token, which makes it the better buy when Qwen3.7 Max's lead doesn't matter for your workload.
Last verified . 19 shared benchmarks.
Meta
Alibaba (Qwen)Summary
- They share 19 benchmarks with published results for both. Llama 4 Scout scores higher in 1 category and Qwen3.7 Max in 8 categories; 9 gaps are clear of the uncertainty.
- The widest gap is in math, where Qwen3.7 Max leads 62.3 to 18.4.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 7.8% for Llama 4 Scout and 95.6% for Qwen3.7 Max.
- Llama 4 Scout is cheaper at $0.10 / $0.30 per million input/output tokens, against $2.50 / $7.50 for Qwen3.7 Max.
- Qwen3.7 Max accepts more context: 1M tokens versus 128K.
- Llama 4 Scout has downloadable open weights; the other is API-only.
Side by side
| Llama 4 Scout | Qwen3.7 Max | |
|---|---|---|
| Provider | Meta | Alibaba (Qwen) |
| Noometry Index | 27.4 | 51.4 |
| Released | 2025-04-05 | 2026-05-19 |
| Weights | Open | Proprietary |
| Context window | 128K | 1M |
| Max output | 4K | 131K |
| Input $ / M tokens | $0.10 | $2.50 |
| Output $ / M tokens | $0.30 | $7.50 |
| Results tracked | 43 | 33 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Qwen3.7 Max leads
Llama 4 Scout: 19.9 (#334), Qwen3.7 Max: 50.2 (#43)
| Benchmark | Llama 4 Scout | Qwen3.7 Max |
|---|---|---|
| SciCode | 17% | 48.8% |
| LMArena Coding | 1286 | 1498 |
| SWE-bench Verified | — | 77.3% |
| SWE-bench Verified (bash only) | 9.1% | — |
| LMArena WebDev | — | 1515 |
| BigCodeBench Complete | 43.1% | — |
| ALE-Bench | — | 1,189 |
Agentic & Tool Use Llama 4 Scout leads
Llama 4 Scout: 24.4 (#109), Qwen3.7 Max: 21.8 (#129)
| Benchmark | Llama 4 Scout | Qwen3.7 Max |
|---|---|---|
| Berkeley Function Calling Leaderboard | 28.1% | — |
| GBAEval | — | 0.4% |
Reasoning Qwen3.7 Max leads
Llama 4 Scout: 9.2 (#339), Qwen3.7 Max: 48.4 (#36)
| Benchmark | Llama 4 Scout | Qwen3.7 Max |
|---|---|---|
| CritPt | 0% | 13.4% |
| LMArena Hard Prompts | 1266 | 1483 |
| DTBench | 57.9% | 92.3% |
| LMCA | 12% | 44% |
| Epoch Capabilities Index | 129.64 | 153.74 |
| ARC-AGI-2 | 0% | — |
| SimpleBench | — | 70.4% |
| Kagi LLM Benchmark | 36.9% | — |
| NYT Connections (extended) | — | 85.1% |
| ARC-AGI-1 | 0.5% | — |
| Chess Puzzles | — | 19% |
| EBR-Bench | — | 9.5% |
| Mystery Game Puzzles | — | 32% |
| ForecastBench | 57.5 | — |
Math Qwen3.7 Max leads
Llama 4 Scout: 18.4 (#280), Qwen3.7 Max: 62.3 (#26)
| Benchmark | Llama 4 Scout | Qwen3.7 Max |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 7.8% | 95.6% |
| LMArena Math | 1286 | 1488 |
| FrontierMath (Tiers 1-3) | — | 64.6% |
| FrontierMath Tier 4 | — | 34.1% |
| ProofBench | — | 26% |
| Omni-MATH | 37.3% | — |
| MATH Level 5 | 62.3% | — |
| FrontierMath (Feb 2025 set) | 0% | — |
Knowledge Qwen3.7 Max leads
Llama 4 Scout: 31.8 (#208), Qwen3.7 Max: 61.7 (#24)
| Benchmark | Llama 4 Scout | Qwen3.7 Max |
|---|---|---|
| GPQA Diamond | 51.8% | 90.9% |
| LMArena Expert | 1236 | 1488 |
| SimpleQA Verified | — | 55.8% |
| MMLU-Pro | 74.2% | — |
| Vectara Hallucination Rate | 7.7% | — |
| GPQA (HELM) | 50.7% | — |
Multimodal Not comparable
Llama 4 Scout: 31.6 (#98), Qwen3.7 Max: —
| Benchmark | Llama 4 Scout | Qwen3.7 Max |
|---|---|---|
| LMArena Vision | 1118 | — |
| SpatialViz-Bench | 34.2% | — |
Multilingual Qwen3.7 Max leads
Llama 4 Scout: 41.3 (#207), Qwen3.7 Max: 57.1 (#13)
| Benchmark | Llama 4 Scout | Qwen3.7 Max |
|---|---|---|
| LMArena Non-English | 1253 | 1475 |
| LMArena Chinese | 1256 | 1533 |
| LMArena Russian | 1263 | 1482 |
| LMArena French | 1283 | — |
| LMArena German | 1274 | — |
| LMArena Japanese | 1209 | — |
| LMArena Korean | 1207 | — |
| LMArena Spanish | 1277 | — |
Instruction Following Qwen3.7 Max leads
Llama 4 Scout: 66.0 (#212), Qwen3.7 Max: 76.9 (#34)
| Benchmark | Llama 4 Scout | Qwen3.7 Max |
|---|---|---|
| LMArena Instruction Following | 1248 | 1460 |
| IFEval | 81.8% | — |
Long Context Qwen3.7 Max leads
Llama 4 Scout: 27.5 (#289), Qwen3.7 Max: 45.4 (#34)
| Benchmark | Llama 4 Scout | Qwen3.7 Max |
|---|---|---|
| LMArena Longer Query | 1265 | 1484 |
| Fiction.LiveBench | 36% | — |
Writing & Preference Qwen3.7 Max leads
Llama 4 Scout: 37.1 (#256), Qwen3.7 Max: 65.2 (#52)
| Benchmark | Llama 4 Scout | Qwen3.7 Max |
|---|---|---|
| LMArena Text | 1279 | 1476 |
| LMArena Creative Writing | 1249 | 1450 |
| LMArena Multi-Turn | 1281 | 1482 |
| EQ-Bench Creative Writing | 783 | — |
| WildBench | 78% | — |
| EQ-Bench 4 | — | 1110 |
Frequently asked questions
Is Llama 4 Scout better than Qwen3.7 Max?
Qwen3.7 Max is the stronger model overall, scoring 51.4 to 27.4 on the Noometry Index. Llama 4 Scout costs 25× less per token, which makes it the better buy when Qwen3.7 Max's lead doesn't matter for your workload.
Which is cheaper, Llama 4 Scout or Qwen3.7 Max?
Llama 4 Scout is cheaper. It lists at $0.10 per million input tokens and $0.30 per million output tokens; Qwen3.7 Max lists at $2.50 and $7.50.
Is Llama 4 Scout or Qwen3.7 Max better for coding?
Qwen3.7 Max scores higher on coding benchmarks: 50.2 versus 19.9 in the Noometry coding category.
Which has the bigger context window?
Qwen3.7 Max does, with 1M tokens against 128K.
How many benchmarks do Llama 4 Scout and Qwen3.7 Max share?
19 benchmarks have published results for both models. Llama 4 Scout has 43 scored results on Noometry and Qwen3.7 Max has 33.