Llama 4 Scout vs Qwen2.5 72B Instruct
Qwen2.5 72B Instruct leads Llama 4 Scout on the Artificial Analysis Intelligence Index, 7.7 to 6.5, and Qwen2.5 72B Instruct costs 1.3x less per output token ($0.40 vs $0.50 per million). Updated October 22, 2026; 43 benchmarks have a result for both.
Llama 4 Scout or Qwen2.5 72B Instruct: which to pick
Neither model has a coding score yet, so the two cannot be ranked on coding.
Pick Llama 4 Scout for a larger context window (1.31M against 33K tokens) and work measured by Terminal-Bench Hard (Artificial Analysis run) or LMArena Text: coding, where it leads.
- Shared results
- 43
- Llama 4 Scout only
- 39
- Qwen2.5 72B Instruct only
- 10
- Like-for-like categories
- 7 of 9
Only benchmarks that tested both models count toward a pick; a result only one model has is shown but not compared.
Which one for your work
Each card is decided by one number both models carry. Where only one has it, the card says so and makes no call.
Coding
Vibe Coding Index, six public coding benchmarks
No call
Neither has a coding score yet.
One side not measured
Intelligence
AA Intelligence Index
Qwen2.5 72B Instruct
Qwen2.5 72B Instruct leads, 7.7 against 6.5.
Same board, both measured
Agentic work
AA Agentic Index
No call
Only Llama 4 Scout has a AA Agentic Index result, 0.5.
Directional only
Reasoning
GPQA Diamond
No call
Only Llama 4 Scout has a GPQA Diamond result, 47.0%.
Directional only
Math
AIME
No call
Only Llama 4 Scout has a AIME result, 19.0%.
Directional only
Knowledge
MMLU Pro
No call
Only Llama 4 Scout has a MMLU Pro result, 69.6%.
Directional only
Web design
Design Arena: websites
No call
Only Llama 4 Scout has a Design Arena: websites result, 750.
Directional only
Long documents
Listed context window
Llama 4 Scout
Llama 4 Scout takes 1.31M tokens against 33K.
Listed by OpenRouter
Everyday cost
1K input + 500 output tokens
Llama 4 Scout
Llama 4 Scout $0.0004, Qwen2.5 72B Instruct $0.0006 per turn.
List prices
Cost per solved task
One SWE-bench Verified task, solved
No call
Only Llama 4 Scout has the number, $1.276.
Directional only
At a glance
- Coding index
- Llama 4 Scout not benchmarked, Qwen2.5 72B Instruct not benchmarked.
- Widest category
- Agentic work, 19.0 points apart on average over 1 shared benchmark.
- Widest single gap
- τ²-Bench Telecom: Llama 4 Scout 15.5% against Qwen2.5 72B Instruct 34.5%, 19.0 points apart on a 0 to 100 scale.
- Output price
- Llama 4 Scout $0.50 against Qwen2.5 72B Instruct $0.40 per million output tokens, 1.3x apart.
- Context window
- Llama 4 Scout takes 1.31M tokens, Qwen2.5 72B Instruct 33K.
Benchmark by benchmark
First the score: boards each model leads, per category, where both have a result. Then every board, a category to a fold; bars are each result on a 0 to 100 scale, so compare the two in a row, not one row with another.
| Category | Llama 4 Scout | Bars | Qwen2.5 72B Instruct | Ties |
|---|---|---|---|---|
| Coding | 1 | 3 | ||
| Intelligence | 1 | 1 | ||
| Agentic work | 0 | 1 | ||
| Reasoning | 4 | 2 | ||
| Math | 1 | 3 | 2 ties | |
| Knowledge | 4 | 1 | ||
| General | 13 | 6 | ||
| All shared boards | 24 | 17 | 2 ties |
CodingLike-for-likeSix of these boards feed the Vibe Coding Index13
| Benchmark | Llama 4 Scout | Qwen2.5 72B Instruct | Leader |
|---|---|---|---|
| SWE-bench Verified | 9.1% | Not measured | Only Llama 4 Scout measured |
| AA Coding Index | 8.2 | Not measured | Only Llama 4 Scout measured |
| LiveCodeBench (Vals AI) | 38.5% | Not measured | Only Llama 4 Scout measured |
| LiveCodeBench (Artificial Analysis run) | 29.9% | 27.6% | Llama 4 Scout |
| SciCode | 21.3% | Not measured | Only Llama 4 Scout measured |
| Terminal-Bench Hard (Artificial Analysis run) | 1.5% | 4.5% | Qwen2.5 72B Instruct |
| WeirdML | Not measured | 16.0% | Only Qwen2.5 72B Instruct measured |
| LMArena Text: coding | 1286 | 1292 | Qwen2.5 72B Instruct |
| LMArena Text: software and IT | 1286 | 1292 | Qwen2.5 72B Instruct |
| Neither model has a result on the other 30 boards here | |||
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index11
| Benchmark | Llama 4 Scout | Qwen2.5 72B Instruct | Leader |
|---|---|---|---|
| AA Intelligence Index | 6.5 | 7.7 | Qwen2.5 72B Instruct |
| Epoch Capabilities Index | 129.6 | 129.0 | Llama 4 Scout |
Agentic workLike-for-likePublic boards, shown as published, kept out of the index01
| Benchmark | Llama 4 Scout | Qwen2.5 72B Instruct | Leader |
|---|---|---|---|
| AA Agentic Index | 0.5 | Not measured | Only Llama 4 Scout measured |
| τ²-Bench Telecom | 15.5% | 34.5% | Qwen2.5 72B Instruct |
| METR time horizons | Not measured | 35.8% | Only Qwen2.5 72B Instruct measured |
| BALROG | Not measured | 16.2% | Only Qwen2.5 72B Instruct measured |
| TheAgentCompany | Not measured | 5.7% | Only Qwen2.5 72B Instruct measured |
| Berkeley Function Calling Leaderboard (BFCL) | 28.1% | Not measured | Only Llama 4 Scout measured |
| Neither model has a result on the other 35 boards here | |||
ReasoningLike-for-likePublic boards, shown as published, kept out of the index42
| Benchmark | Llama 4 Scout | Qwen2.5 72B Instruct | Leader |
|---|---|---|---|
| GPQA Diamond | 47.0% | Not measured | Only Llama 4 Scout measured |
| MMMU Pro (Vals AI) | 58.8% | Not measured | Only Llama 4 Scout measured |
| GPQA Diamond (Artificial Analysis run) | 58.7% | 49.1% | Llama 4 Scout |
| Humanity's Last Exam (Artificial Analysis run) | 3.8% | 3.6% | Llama 4 Scout |
| GPQA Diamond (Epoch AI run) | 51.8% | 49.1% | Llama 4 Scout |
| ARC-AGI | 0.5% | Not measured | Only Llama 4 Scout measured |
| ARC-AGI-2 | 0.0% | Not measured | Only Llama 4 Scout measured |
| BIG-Bench Hard | Not measured | 79.8% | Only Qwen2.5 72B Instruct measured |
| LMArena Text: hard prompts | 1266 | 1271 | Qwen2.5 72B Instruct |
| LMArena Text: expert | 1235 | 1245 | Qwen2.5 72B Instruct |
| LMArena Text: hard prompts in English | 1293 | 1279 | Llama 4 Scout |
| LMArena Vision: diagrams | 1125 | Not measured | Only Llama 4 Scout measured |
| LMArena Vision: homework | 1148 | Not measured | Only Llama 4 Scout measured |
| Kagi LLM Benchmark | 36.9% | Not measured | Only Llama 4 Scout measured |
| Neither model has a result on the other 8 boards here | |||
MathLike-for-likePublic boards, shown as published, kept out of the index13
| Benchmark | Llama 4 Scout | Qwen2.5 72B Instruct | Leader |
|---|---|---|---|
| AIME | 19.0% | Not measured | Only Llama 4 Scout measured |
| MATH 500 (Vals AI) | 79.2% | Not measured | Only Llama 4 Scout measured |
| MGSM (Vals AI) | 88.0% | Not measured | Only Llama 4 Scout measured |
| AA Math Index | 14.0 | 14.0 | Tie |
| AIME 2025 (Artificial Analysis run) | 14.0% | 14.0% | Tie |
| OTIS Mock AIME | 7.8% | 8.1% | Qwen2.5 72B Instruct |
| MATH level 5 | 62.3% | 63.2% | Qwen2.5 72B Instruct |
| LMArena Text: math | 1287 | 1283 | Llama 4 Scout |
| LMArena Text: mathematical work | 1286 | 1290 | Qwen2.5 72B Instruct |
| Neither model has a result on the other 4 boards here | |||
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index41
| Benchmark | Llama 4 Scout | Qwen2.5 72B Instruct | Leader |
|---|---|---|---|
| MMLU Pro | 69.6% | Not measured | Only Llama 4 Scout measured |
| LegalBench (Vals AI) | 72.0% | Not measured | Only Llama 4 Scout measured |
| CorpFin (Vals AI) | 46.8% | Not measured | Only Llama 4 Scout measured |
| TaxEval (Vals AI) | 55.2% | Not measured | Only Llama 4 Scout measured |
| MortgageTax (Vals AI) | 57.8% | Not measured | Only Llama 4 Scout measured |
| MedQA (Vals AI) | 50.9% | Not measured | Only Llama 4 Scout measured |
| MedCode (Vals AI) | 23.3% | Not measured | Only Llama 4 Scout measured |
| MMLU Pro (Artificial Analysis run) | 75.2% | 72.0% | Llama 4 Scout |
| MMLU | Not measured | 85.3% | Only Qwen2.5 72B Instruct measured |
| AI2 Reasoning Challenge | Not measured | 94.5% | Only Qwen2.5 72B Instruct measured |
| LMArena Text: science | 1278 | 1275 | Llama 4 Scout |
| LMArena Text: medicine and healthcare | 1275 | 1258 | Llama 4 Scout |
| LMArena Text: legal and government | 1285 | 1288 | Qwen2.5 72B Instruct |
| LMArena Text: business and finance | 1257 | 1253 | Llama 4 Scout |
| Neither model has a result on the other 4 boards here | |||
Web designDirectional onlyPublic boards, shown as published, kept out of the index5 boards, none shared
| Benchmark | Llama 4 Scout | Qwen2.5 72B Instruct | Leader |
|---|---|---|---|
| Design Arena: websites | 750 | Not measured | Only Llama 4 Scout measured |
| Design Arena: UI components | 765 | Not measured | Only Llama 4 Scout measured |
| Design Arena: game dev | 772 | Not measured | Only Llama 4 Scout measured |
| Design Arena: data viz | 896 | Not measured | Only Llama 4 Scout measured |
| Design Arena: all code categories | 789 | Not measured | Only Llama 4 Scout measured |
| Neither model has a result on the other 4 boards here | |||
GeneralLike-for-likePublic boards, shown as published, kept out of the index136
| Benchmark | Llama 4 Scout | Qwen2.5 72B Instruct | Leader |
|---|---|---|---|
| SAGE (Vals AI) | 34.8% | Not measured | Only Llama 4 Scout measured |
| MedScribe (Vals AI) | 50.6% | Not measured | Only Llama 4 Scout measured |
| IFBench | 39.5% | 36.9% | Llama 4 Scout |
| Long context reasoning (AA-LCR) | 27.7% | Not measured | Only Llama 4 Scout measured |
| DTBench | 57.9% | 62.9% | Qwen2.5 72B Instruct |
| LMCA | 12.0% | 13.4% | Qwen2.5 72B Instruct |
| Fiction.LiveBench | 36.0% | Not measured | Only Llama 4 Scout measured |
| HellaSwag | Not measured | 84.8% | Only Qwen2.5 72B Instruct measured |
| WinoGrande | Not measured | 82.3% | Only Qwen2.5 72B Instruct measured |
| PIQA | Not measured | 82.6% | Only Qwen2.5 72B Instruct measured |
| LMArena Text | 1279 | 1269 | Llama 4 Scout |
| LMArena Text: instruction following | 1248 | 1254 | Qwen2.5 72B Instruct |
| LMArena Text: creative writing | 1249 | 1221 | Llama 4 Scout |
| LMArena Vision | 1118 | Not measured | Only Llama 4 Scout measured |
| LMArena Text: English | 1304 | 1283 | Llama 4 Scout |
| LMArena Text: non-English | 1252 | 1252 | Llama 4 Scout |
| LMArena Text: Chinese | 1255 | 1273 | Qwen2.5 72B Instruct |
| LMArena Text: German | 1273 | 1234 | Llama 4 Scout |
| LMArena Text: Japanese | 1206 | 1180 | Llama 4 Scout |
| LMArena Text: Korean | 1207 | 1188 | Llama 4 Scout |
| LMArena Text: French | 1283 | 1280 | Llama 4 Scout |
| LMArena Text: Spanish | 1278 | 1255 | Llama 4 Scout |
| LMArena Text: Russian | 1263 | 1264 | Qwen2.5 72B Instruct |
| LMArena Text: Polish | 1265 | Not measured | Only Llama 4 Scout measured |
| LMArena Text: multi-turn | 1280 | 1272 | Llama 4 Scout |
| LMArena Text: longer queries | 1265 | 1281 | Qwen2.5 72B Instruct |
| LMArena Text: writing and language | 1269 | 1247 | Llama 4 Scout |
| LMArena Text: entertainment and media | 1242 | 1211 | Llama 4 Scout |
| LMArena Vision: English | 1143 | Not measured | Only Llama 4 Scout measured |
| LMArena Vision: Chinese | 1106 | Not measured | Only Llama 4 Scout measured |
| LMArena Vision: reading text | 1117 | Not measured | Only Llama 4 Scout measured |
| LMArena Vision: humor | 1102 | Not measured | Only Llama 4 Scout measured |
| LMArena Vision: creative writing | 1126 | Not measured | Only Llama 4 Scout measured |
| Neither model has a result on the other 13 boards here | |||
Image generationNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
| Benchmark | Llama 4 Scout | Qwen2.5 72B Instruct | Leader |
|---|---|---|---|
| Neither model has a result on 5 boards here | |||
What each workload costs
Three fixed token mixes at each model's listed price, so per-token rates become a bill.
Chat turn
1K input + 500 output tokens
Llama 4 Scout costs less
Repository review
50K input + 3K output tokens
Llama 4 Scout costs less
Agent loop
200K input + 10K output tokens
Llama 4 Scout costs less
Listed OpenRouter rates, without cache or batch discounts. A workload that does not fit a model's context window would need splitting.
Specification differences
The leading value in a row is marked; a row with a missing value names no leader. Our two rows are marked in red.
| Specification | Meta Llama 4 Scout | Qwen2.5 72B Instruct |
|---|---|---|
| Maker | Meta Llama | Qwen |
| Weights | Open weights | Open weights |
| Released | April 5, 2025 | September 19, 2024 |
| Context window | 1.31M | 33K |
| Input $/Mtok | $0.175 | $0.36 |
| Output $/Mtok | $0.50 | $0.40 |
| Coding index | Not benchmarked | Not benchmarked |
| Independent measurements behind it | 0 | 0 |
| Cost per solved task | $1.276 | Not computable |
| Source | OpenRouter listing | OpenRouter listing |
Questions
Is Llama 4 Scout better than Qwen2.5 72B Instruct for coding?
Neither model has a coding score yet, so the two cannot be ranked on coding. Pick Llama 4 Scout for a larger context window (1.31M against 33K tokens) and work measured by Terminal-Bench Hard (Artificial Analysis run) or LMArena Text: coding, where it leads.
Which is cheaper, Llama 4 Scout or Qwen2.5 72B Instruct?
Llama 4 Scout costs $0.175 per million input tokens and $0.50 per million output tokens; Qwen2.5 72B Instruct costs $0.36 and $0.40. Cost per solved task is known for Llama 4 Scout only.
Which has the bigger context window, Llama 4 Scout or Qwen2.5 72B Instruct?
Llama 4 Scout, with 1.31M tokens against 33K.
How many benchmarks is the Llama 4 Scout vs Qwen2.5 72B Instruct comparison based on?
43 benchmarks have a result for both models as of October 22, 2026. Llama 4 Scout's coding index rests on 0 independent benchmarks and Qwen2.5 72B Instruct's on 0. Where only one model has a result, the page says so instead of naming a winner.