Model comparison
Llama 4 Scout vs Qwen2.5 7B Instruct
Qwen2.5 7B Instruct is the stronger model overall, scoring 28.6 to 27.4 on the Noometry Index. Llama 4 Scout costs 2.0× less per token, which makes it the better buy when Qwen2.5 7B Instruct's lead doesn't matter for your workload.
Last verified . 11 shared benchmarks.
Meta
Alibaba (Qwen)Summary
- They share 11 benchmarks with published results for both. Llama 4 Scout scores higher in 4 categories and Qwen2.5 7B Instruct in 3 categories; 6 gaps are clear of the uncertainty.
- The widest gap is in coding, where Qwen2.5 7B Instruct leads 35.9 to 19.9.
- The biggest single-benchmark swing is MMLU-Pro: 74.2% for Llama 4 Scout and 53.9% for Qwen2.5 7B Instruct.
- Llama 4 Scout is cheaper at $0.10 / $0.30 per million input/output tokens, against $0.17 / $0.70 for Qwen2.5 7B Instruct.
- Qwen2.5 7B Instruct accepts more context: 131K tokens versus 128K.
Side by side
| Llama 4 Scout | Qwen2.5 7B Instruct | |
|---|---|---|
| Provider | Meta | Alibaba (Qwen) |
| Noometry Index | 27.4 | 28.6 |
| Released | 2025-04-05 | 2024-09 |
| Weights | Open | Open |
| Context window | 128K | 131K |
| Max output | 4K | 8K |
| Input $ / M tokens | $0.10 | $0.17 |
| Output $ / M tokens | $0.30 | $0.70 |
| Results tracked | 43 | 15 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Qwen2.5 7B Instruct leads
Llama 4 Scout: 19.9 (#334), Qwen2.5 7B Instruct: 35.9 (#204)
| Benchmark | Llama 4 Scout | Qwen2.5 7B Instruct |
|---|---|---|
| BigCodeBench Complete | 43.1% | 46.1% |
| SWE-bench Verified (bash only) | 9.1% | — |
| SciCode | 17% | — |
| BigCodeBench Instruct | — | 37.6% |
| LMArena Coding | 1286 | — |
Agentic & Tool Use Too close to call
Llama 4 Scout: 24.4 (#109), Qwen2.5 7B Instruct: 23.5 (#117)
| Benchmark | Llama 4 Scout | Qwen2.5 7B Instruct |
|---|---|---|
| Berkeley Function Calling Leaderboard | 28.1% | — |
| BALROG | — | 7.8% |
Reasoning Qwen2.5 7B Instruct leads
Llama 4 Scout: 9.2 (#339), Qwen2.5 7B Instruct: 14.3 (#317)
| Benchmark | Llama 4 Scout | Qwen2.5 7B Instruct |
|---|---|---|
| DTBench | 57.9% | 47.7% |
| LMCA | 12% | 6.4% |
| Epoch Capabilities Index | 129.64 | 118.44 |
| ARC-AGI-2 | 0% | — |
| Kagi LLM Benchmark | 36.9% | — |
| ARC-AGI-1 | 0.5% | — |
| CritPt | 0% | — |
| Chess Puzzles | — | 0% |
| LMArena Hard Prompts | 1266 | — |
| ForecastBench | 57.5 | — |
Math Llama 4 Scout leads
Llama 4 Scout: 18.4 (#280), Qwen2.5 7B Instruct: 11.8 (#300)
| Benchmark | Llama 4 Scout | Qwen2.5 7B Instruct |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 7.8% | 2.5% |
| Omni-MATH | 37.3% | 29.4% |
| LMArena Math | 1286 | — |
| MATH Level 5 | 62.3% | — |
| FrontierMath (Feb 2025 set) | 0% | — |
Knowledge Llama 4 Scout leads
Llama 4 Scout: 31.8 (#208), Qwen2.5 7B Instruct: 17.0 (#281)
| Benchmark | Llama 4 Scout | Qwen2.5 7B Instruct |
|---|---|---|
| GPQA Diamond | 51.8% | 35.5% |
| MMLU-Pro | 74.2% | 53.9% |
| GPQA (HELM) | 50.7% | 34.1% |
| Vectara Hallucination Rate | 7.7% | — |
| LMArena Expert | 1236 | — |
| MMLU | — | 72.9% |
Multimodal Not comparable
Llama 4 Scout: 31.6 (#98), Qwen2.5 7B Instruct: —
| Benchmark | Llama 4 Scout | Qwen2.5 7B Instruct |
|---|---|---|
| LMArena Vision | 1118 | — |
| SpatialViz-Bench | 34.2% | — |
Multilingual Not comparable
Llama 4 Scout: 41.3 (#207), Qwen2.5 7B Instruct: —
| Benchmark | Llama 4 Scout | Qwen2.5 7B Instruct |
|---|---|---|
| LMArena Non-English | 1253 | — |
| LMArena Chinese | 1256 | — |
| LMArena French | 1283 | — |
| LMArena German | 1274 | — |
| LMArena Japanese | 1209 | — |
| LMArena Korean | 1207 | — |
| LMArena Russian | 1263 | — |
| LMArena Spanish | 1277 | — |
Instruction Following Llama 4 Scout leads
Llama 4 Scout: 66.0 (#212), Qwen2.5 7B Instruct: 63.4 (#226)
| Benchmark | Llama 4 Scout | Qwen2.5 7B Instruct |
|---|---|---|
| IFEval | 81.8% | 74.1% |
| LMArena Instruction Following | 1248 | — |
Long Context Not comparable
Llama 4 Scout: 27.5 (#289), Qwen2.5 7B Instruct: —
| Benchmark | Llama 4 Scout | Qwen2.5 7B Instruct |
|---|---|---|
| Fiction.LiveBench | 36% | — |
| LMArena Longer Query | 1265 | — |
Writing & Preference Qwen2.5 7B Instruct leads
Llama 4 Scout: 37.1 (#256), Qwen2.5 7B Instruct: 48.8 (#194)
| Benchmark | Llama 4 Scout | Qwen2.5 7B Instruct |
|---|---|---|
| WildBench | 78% | 73.1% |
| LMArena Text | 1279 | — |
| LMArena Creative Writing | 1249 | — |
| EQ-Bench Creative Writing | 783 | — |
| LMArena Multi-Turn | 1281 | — |
Frequently asked questions
Is Llama 4 Scout better than Qwen2.5 7B Instruct?
Qwen2.5 7B Instruct is the stronger model overall, scoring 28.6 to 27.4 on the Noometry Index. Llama 4 Scout costs 2.0× less per token, which makes it the better buy when Qwen2.5 7B Instruct's lead doesn't matter for your workload.
Which is cheaper, Llama 4 Scout or Qwen2.5 7B Instruct?
Llama 4 Scout is cheaper. It lists at $0.10 per million input tokens and $0.30 per million output tokens; Qwen2.5 7B Instruct lists at $0.17 and $0.70.
Is Llama 4 Scout or Qwen2.5 7B Instruct better for coding?
Qwen2.5 7B Instruct scores higher on coding benchmarks: 35.9 versus 19.9 in the Noometry coding category.
Which has the bigger context window?
Qwen2.5 7B Instruct does, with 131K tokens against 128K.
How many benchmarks do Llama 4 Scout and Qwen2.5 7B Instruct share?
11 benchmarks have published results for both models. Llama 4 Scout has 43 scored results on Noometry and Qwen2.5 7B Instruct has 15.