Model comparison
Llama 4 Scout vs Qwen3.5 35B-A3B
Qwen3.5 35B-A3B is the stronger model overall, scoring 42.0 to 27.7 on the Noometry Index. Llama 4 Scout costs 4.6× less per token, which makes it the better buy when Qwen3.5 35B-A3B's lead doesn't matter for your workload.
Last verified . 25 shared benchmarks.
Meta
Alibaba (Qwen)Summary
- They share 25 benchmarks with published results for both. Llama 4 Scout scores higher in 0 categories and Qwen3.5 35B-A3B in 8 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Qwen3.5 35B-A3B leads 57.9 to 37.0.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 7.8% for Llama 4 Scout and 70% for Qwen3.5 35B-A3B.
- Llama 4 Scout is cheaper at $0.10 / $0.30 per million input/output tokens, against $0.25 / $2 for Qwen3.5 35B-A3B.
- Qwen3.5 35B-A3B accepts more context: 262K tokens versus 128K.
Side by side
| Llama 4 Scout | Qwen3.5 35B-A3B | |
|---|---|---|
| Provider | Meta | Alibaba (Qwen) |
| Noometry Index | 27.7 | 42.0 |
| Released | 2025-04-05 | 2026-02-01 |
| Weights | Open | Open |
| Context window | 128K | 262K |
| Max output | 4K | 66K |
| Input $ / M tokens | $0.10 | $0.25 |
| Output $ / M tokens | $0.30 | $2 |
| Results tracked | 43 | 28 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Qwen3.5 35B-A3B leads
Llama 4 Scout: 20.2 (#339), Qwen3.5 35B-A3B: 33.8 (#251)
| Benchmark | Llama 4 Scout | Qwen3.5 35B-A3B |
|---|---|---|
| SciCode | 17% | 29.3% |
| LMArena Coding | 1286 | 1410 |
| SWE-bench Verified (bash only) | 9.1% | — |
| LMArena WebDev | — | 1254 |
| BigCodeBench Complete | 43.1% | — |
Agentic & Tool Use Not comparable
Llama 4 Scout: 24.6 (#119), Qwen3.5 35B-A3B: —
| Benchmark | Llama 4 Scout | Qwen3.5 35B-A3B |
|---|---|---|
| Berkeley Function Calling Leaderboard | 28.1% | — |
Reasoning Qwen3.5 35B-A3B leads
Llama 4 Scout: 9.1 (#345), Qwen3.5 35B-A3B: 24.6 (#161)
| Benchmark | Llama 4 Scout | Qwen3.5 35B-A3B |
|---|---|---|
| CritPt | 0% | 0.6% |
| LMArena Hard Prompts | 1266 | 1400 |
| DTBench | 57.9% | 80% |
| LMCA | 12% | 29.5% |
| Epoch Capabilities Index | 129.64 | 142.52 |
| ARC-AGI-2 | 0% | — |
| Kagi LLM Benchmark | 36.9% | — |
| ARC-AGI-1 | 0.5% | — |
| Chess Puzzles | — | 10% |
| ForecastBench | 57.5 | — |
Math Qwen3.5 35B-A3B leads
Llama 4 Scout: 19.6 (#286), Qwen3.5 35B-A3B: 39.9 (#97)
| Benchmark | Llama 4 Scout | Qwen3.5 35B-A3B |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 7.8% | 70% |
| LMArena Math | 1287 | 1404 |
| MathArena Final-Answer Competitions | — | 56% |
| Omni-MATH | 37.3% | — |
| MATH Level 5 | 62.3% | — |
| FrontierMath (Feb 2025 set) | 0% | — |
Knowledge Qwen3.5 35B-A3B leads
Llama 4 Scout: 31.9 (#217), Qwen3.5 35B-A3B: 47.8 (#79)
| Benchmark | Llama 4 Scout | Qwen3.5 35B-A3B |
|---|---|---|
| GPQA Diamond | 51.8% | 83.5% |
| Vectara Hallucination Rate | 7.7% | 10.5% |
| LMArena Expert | 1235 | 1408 |
| MMLU-Pro | 74.2% | — |
| GPQA (HELM) | 50.7% | — |
Multimodal Not comparable
Llama 4 Scout: 32.2 (#102), Qwen3.5 35B-A3B: —
| Benchmark | Llama 4 Scout | Qwen3.5 35B-A3B |
|---|---|---|
| LMArena Vision | 1118 | — |
| SpatialViz-Bench | 34.2% | — |
Multilingual Qwen3.5 35B-A3B leads
Llama 4 Scout: 41.0 (#212), Qwen3.5 35B-A3B: 50.0 (#127)
| Benchmark | Llama 4 Scout | Qwen3.5 35B-A3B |
|---|---|---|
| LMArena Non-English | 1252 | 1378 |
| LMArena Chinese | 1255 | 1457 |
| LMArena French | 1282 | 1412 |
| LMArena German | 1272 | 1367 |
| LMArena Japanese | 1206 | 1325 |
| LMArena Korean | 1207 | 1356 |
| LMArena Russian | 1263 | 1376 |
| LMArena Spanish | 1278 | 1392 |
Instruction Following Qwen3.5 35B-A3B leads
Llama 4 Scout: 65.8 (#217), Qwen3.5 35B-A3B: 72.8 (#128)
| Benchmark | Llama 4 Scout | Qwen3.5 35B-A3B |
|---|---|---|
| LMArena Instruction Following | 1248 | 1379 |
| IFEval | 81.8% | — |
Long Context Qwen3.5 35B-A3B leads
Llama 4 Scout: 27.5 (#294), Qwen3.5 35B-A3B: 42.4 (#127)
| Benchmark | Llama 4 Scout | Qwen3.5 35B-A3B |
|---|---|---|
| LMArena Longer Query | 1265 | 1389 |
| Fiction.LiveBench | 36% | — |
Writing & Preference Qwen3.5 35B-A3B leads
Llama 4 Scout: 37.0 (#261), Qwen3.5 35B-A3B: 57.9 (#124)
| Benchmark | Llama 4 Scout | Qwen3.5 35B-A3B |
|---|---|---|
| LMArena Text | 1279 | 1395 |
| LMArena Creative Writing | 1249 | 1346 |
| LMArena Multi-Turn | 1280 | 1390 |
| EQ-Bench Creative Writing | 783 | — |
| WildBench | 78% | — |
Frequently asked questions
Is Llama 4 Scout better than Qwen3.5 35B-A3B?
Qwen3.5 35B-A3B is the stronger model overall, scoring 42.0 to 27.7 on the Noometry Index. Llama 4 Scout costs 4.6× less per token, which makes it the better buy when Qwen3.5 35B-A3B's lead doesn't matter for your workload.
Which is cheaper, Llama 4 Scout or Qwen3.5 35B-A3B?
Llama 4 Scout is cheaper. It lists at $0.10 per million input tokens and $0.30 per million output tokens; Qwen3.5 35B-A3B lists at $0.25 and $2.
Is Llama 4 Scout or Qwen3.5 35B-A3B better for coding?
Qwen3.5 35B-A3B scores higher on coding benchmarks: 33.8 versus 20.2 in the Noometry coding category.
Which has the bigger context window?
Qwen3.5 35B-A3B does, with 262K tokens against 128K.
How many benchmarks do Llama 4 Scout and Qwen3.5 35B-A3B share?
25 benchmarks have published results for both models. Llama 4 Scout has 43 scored results on Noometry and Qwen3.5 35B-A3B has 28.