Llama 4 Maverick vs Qwen3.5 397B A17B
Qwen3.5 397B A17B leads Llama 4 Maverick on the Artificial Analysis Intelligence Index, 21.4 to 9.3, and Llama 4 Maverick costs 2.3x less per output token ($1.00 vs $2.34 per million). Updated October 22, 2026; 54 benchmarks have a result for both.
Llama 4 Maverick or Qwen3.5 397B A17B: which to pick
Neither model has a coding score yet, so the two cannot be ranked on coding.
Pick Llama 4 Maverick for output tokens 2.3x cheaper ($1.00 vs $2.34 per million) and a larger context window (524K against 262K tokens).
- Shared results
- 54
- Llama 4 Maverick only
- 31
- Qwen3.5 397B A17B only
- 12
- Like-for-like categories
- 8 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
Qwen3.5 397B A17B
Qwen3.5 397B A17B leads, 21.4 against 9.3.
Same board, both measured
Agentic work
AA Agentic Index
No call
Only Llama 4 Maverick has a AA Agentic Index result, 0.6.
Directional only
Reasoning
GPQA Diamond
No call
Only Llama 4 Maverick has a GPQA Diamond result, 69.4%.
Directional only
Math
AIME
No call
Only Llama 4 Maverick has a AIME result, 25.2%.
Directional only
Knowledge
MMLU Pro
No call
Only Llama 4 Maverick has a MMLU Pro result, 79.4%.
Directional only
Web design
Design Arena: websites
Qwen3.5 397B A17B
Qwen3.5 397B A17B leads, 1190 against 871.
Same board, both measured
Long documents
Listed context window
Llama 4 Maverick
Llama 4 Maverick takes 524K tokens against 262K.
Listed by OpenRouter
Everyday cost
1K input + 500 output tokens
Llama 4 Maverick
Llama 4 Maverick $0.0008, Qwen3.5 397B A17B $0.0016 per turn.
List prices
Cost per solved task
One SWE-bench Verified task, solved
No call
Only Llama 4 Maverick has the number, $1.491.
Directional only
At a glance
- Coding index
- Llama 4 Maverick not benchmarked, Qwen3.5 397B A17B not benchmarked.
- Widest category
- Agentic work, 77.8 points apart on average over 1 shared benchmark.
- Widest single gap
- τ²-Bench Telecom: Llama 4 Maverick 17.8% against Qwen3.5 397B A17B 95.6%, 77.8 points apart on a 0 to 100 scale.
- Output price
- Llama 4 Maverick $1.00 against Qwen3.5 397B A17B $2.34 per million output tokens, 2.3x apart.
- Context window
- Llama 4 Maverick takes 524K tokens, Qwen3.5 397B A17B 262K.
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 Maverick | Bars | Qwen3.5 397B A17B | Ties |
|---|---|---|---|---|
| Coding | 0 | 5 | ||
| Intelligence | 0 | 2 | ||
| Agentic work | 0 | 1 | ||
| Reasoning | 0 | 7 | ||
| Math | 0 | 2 | ||
| Knowledge | 0 | 4 | ||
| Web design | 0 | 6 | ||
| General | 0 | 27 | ||
| All shared boards | 0 | 54 |
CodingLike-for-likeSix of these boards feed the Vibe Coding Index05
| Benchmark | Llama 4 Maverick | Qwen3.5 397B A17B | Leader |
|---|---|---|---|
| Aider polyglot | 15.6% | Not measured | Only Llama 4 Maverick measured |
| SWE-bench Verified | 21.0% | Not measured | Only Llama 4 Maverick measured |
| LMArena WebDev | Not measured | 1400 | Only Qwen3.5 397B A17B measured |
| AA Coding Index | 16.3 | Not measured | Only Llama 4 Maverick measured |
| LiveCodeBench (Vals AI) | 47.3% | Not measured | Only Llama 4 Maverick measured |
| LiveCodeBench (Artificial Analysis run) | 39.7% | Not measured | Only Llama 4 Maverick measured |
| SciCode | 31.7% | 44.8% | Qwen3.5 397B A17B |
| Terminal-Bench Hard (Artificial Analysis run) | 6.8% | 40.9% | Qwen3.5 397B A17B |
| WeirdML | 24.5% | Not measured | Only Llama 4 Maverick measured |
| ALE-Bench | 173.0 | 621.9 | Qwen3.5 397B A17B |
| LMArena Text: coding | 1301 | 1464 | Qwen3.5 397B A17B |
| LMArena Text: software and IT | 1299 | 1463 | Qwen3.5 397B A17B |
| LMArena WebDev: React | Not measured | 1388 | Only Qwen3.5 397B A17B measured |
| LMArena WebDev: HTML | Not measured | 1410 | Only Qwen3.5 397B A17B measured |
| Neither model has a result on the other 29 boards here | |||
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index02
| Benchmark | Llama 4 Maverick | Qwen3.5 397B A17B | Leader |
|---|---|---|---|
| AA Intelligence Index | 9.3 | 21.4 | Qwen3.5 397B A17B |
| Epoch Capabilities Index | 132.2 | 146.8 | Qwen3.5 397B A17B |
Agentic workLike-for-likePublic boards, shown as published, kept out of the index01
| Benchmark | Llama 4 Maverick | Qwen3.5 397B A17B | Leader |
|---|---|---|---|
| AA Agentic Index | 0.6 | Not measured | Only Llama 4 Maverick measured |
| τ²-Bench Telecom | 17.8% | 95.6% | Qwen3.5 397B A17B |
| APEX-Agents | Not measured | 24.9% | Only Qwen3.5 397B A17B measured |
| Neither model has a result on the other 39 boards here | |||
ReasoningLike-for-likePublic boards, shown as published, kept out of the index07
| Benchmark | Llama 4 Maverick | Qwen3.5 397B A17B | Leader |
|---|---|---|---|
| GPQA Diamond | 69.4% | Not measured | Only Llama 4 Maverick measured |
| MMMU Pro (Vals AI) | 71.7% | Not measured | Only Llama 4 Maverick measured |
| GPQA Diamond (Artificial Analysis run) | 67.1% | 89.3% | Qwen3.5 397B A17B |
| Humanity's Last Exam (Artificial Analysis run) | 4.9% | 29.0% | Qwen3.5 397B A17B |
| GPQA Diamond (Epoch AI run) | Not measured | 86.4% | Only Qwen3.5 397B A17B measured |
| ARC-AGI | 4.4% | Not measured | Only Llama 4 Maverick measured |
| ARC-AGI-2 | 0.0% | Not measured | Only Llama 4 Maverick measured |
| SimpleBench | 27.7% | Not measured | Only Llama 4 Maverick measured |
| Mystery game puzzles | Not measured | 18.0% | Only Qwen3.5 397B A17B measured |
| LMArena Text: hard prompts | 1281 | 1448 | Qwen3.5 397B A17B |
| LMArena Text: expert | 1259 | 1462 | Qwen3.5 397B A17B |
| LMArena Text: hard prompts in English | 1295 | 1450 | Qwen3.5 397B A17B |
| LMArena Vision: diagrams | 1134 | 1277 | Qwen3.5 397B A17B |
| LMArena Vision: homework | 1164 | 1292 | Qwen3.5 397B A17B |
| Kagi LLM Benchmark | 55.9% | Not measured | Only Llama 4 Maverick measured |
| Neither model has a result on the other 8 boards here | |||
MathLike-for-likePublic boards, shown as published, kept out of the index02
| Benchmark | Llama 4 Maverick | Qwen3.5 397B A17B | Leader |
|---|---|---|---|
| AIME | 25.2% | Not measured | Only Llama 4 Maverick measured |
| MATH 500 (Vals AI) | 85.2% | Not measured | Only Llama 4 Maverick measured |
| MGSM (Vals AI) | 92.4% | Not measured | Only Llama 4 Maverick measured |
| AA Math Index | 19.3 | Not measured | Only Llama 4 Maverick measured |
| AIME 2025 (Artificial Analysis run) | 19.3% | Not measured | Only Llama 4 Maverick measured |
| OTIS Mock AIME | Not measured | 88.9% | Only Qwen3.5 397B A17B measured |
| FrontierMath, tiers 1 to 3 | Not measured | 31.2% | Only Qwen3.5 397B A17B measured |
| LMArena Text: math | 1299 | 1453 | Qwen3.5 397B A17B |
| LMArena Text: mathematical work | 1295 | 1454 | Qwen3.5 397B A17B |
| MathArena | Not measured | 19.2% | Only Qwen3.5 397B A17B measured |
| Neither model has a result on the other 4 boards here | |||
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index04
| Benchmark | Llama 4 Maverick | Qwen3.5 397B A17B | Leader |
|---|---|---|---|
| MMLU Pro | 79.4% | Not measured | Only Llama 4 Maverick measured |
| LegalBench (Vals AI) | 77.8% | Not measured | Only Llama 4 Maverick measured |
| CorpFin (Vals AI) | 49.7% | Not measured | Only Llama 4 Maverick measured |
| TaxEval (Vals AI) | 66.6% | Not measured | Only Llama 4 Maverick measured |
| MortgageTax (Vals AI) | 58.5% | Not measured | Only Llama 4 Maverick measured |
| MedQA (Vals AI) | 43.3% | Not measured | Only Llama 4 Maverick measured |
| MedCode (Vals AI) | 36.5% | Not measured | Only Llama 4 Maverick measured |
| MMLU Pro (Artificial Analysis run) | 80.9% | Not measured | Only Llama 4 Maverick measured |
| GeoBench | 52.0% | Not measured | Only Llama 4 Maverick measured |
| LMArena Text: science | 1288 | 1457 | Qwen3.5 397B A17B |
| LMArena Text: medicine and healthcare | 1275 | 1455 | Qwen3.5 397B A17B |
| LMArena Text: legal and government | 1286 | 1441 | Qwen3.5 397B A17B |
| LMArena Text: business and finance | 1260 | 1435 | Qwen3.5 397B A17B |
| Neither model has a result on the other 7 boards here | |||
Web designLike-for-likePublic boards, shown as published, kept out of the index06
| Benchmark | Llama 4 Maverick | Qwen3.5 397B A17B | Leader |
|---|---|---|---|
| Design Arena: websites | 871 | 1190 | Qwen3.5 397B A17B |
| Design Arena: UI components | 897 | 1161 | Qwen3.5 397B A17B |
| Design Arena: game dev | 837 | 1140 | Qwen3.5 397B A17B |
| Design Arena: data viz | 882 | 1175 | Qwen3.5 397B A17B |
| Design Arena: 3D | 900 | 1160 | Qwen3.5 397B A17B |
| Design Arena: all code categories | 879 | 1179 | Qwen3.5 397B A17B |
| Design Arena: SVG | Not measured | 1139 | Only Qwen3.5 397B A17B measured |
| Neither model has a result on the other 2 boards here | |||
GeneralLike-for-likePublic boards, shown as published, kept out of the index027
| Benchmark | Llama 4 Maverick | Qwen3.5 397B A17B | Leader |
|---|---|---|---|
| SAGE (Vals AI) | 35.7% | Not measured | Only Llama 4 Maverick measured |
| MedScribe (Vals AI) | 54.2% | Not measured | Only Llama 4 Maverick measured |
| IFBench | 43.0% | 78.8% | Qwen3.5 397B A17B |
| Long context reasoning (AA-LCR) | 50.0% | 77.3% | Qwen3.5 397B A17B |
| DTBench | 61.9% | 87.5% | Qwen3.5 397B A17B |
| LMCA | 15.9% | 37.9% | Qwen3.5 397B A17B |
| Fiction.LiveBench | 46.2% | Not measured | Only Llama 4 Maverick measured |
| Creative writing (Lech Mazur) | 62.0% | Not measured | Only Llama 4 Maverick measured |
| LMArena Text | 1287 | 1437 | Qwen3.5 397B A17B |
| LMArena Text: instruction following | 1267 | 1424 | Qwen3.5 397B A17B |
| LMArena Text: creative writing | 1266 | 1402 | Qwen3.5 397B A17B |
| LMArena Vision | 1142 | 1262 | Qwen3.5 397B A17B |
| LMArena Text: English | 1303 | 1443 | Qwen3.5 397B A17B |
| LMArena Text: non-English | 1269 | 1430 | Qwen3.5 397B A17B |
| LMArena Text: Chinese | 1277 | 1498 | Qwen3.5 397B A17B |
| LMArena Text: German | 1291 | 1445 | Qwen3.5 397B A17B |
| LMArena Text: Japanese | 1206 | 1429 | Qwen3.5 397B A17B |
| LMArena Text: Korean | 1203 | 1384 | Qwen3.5 397B A17B |
| LMArena Text: French | 1259 | 1462 | Qwen3.5 397B A17B |
| LMArena Text: Spanish | 1293 | 1441 | Qwen3.5 397B A17B |
| LMArena Text: Russian | 1286 | 1430 | Qwen3.5 397B A17B |
| LMArena Text: Polish | 1275 | 1447 | Qwen3.5 397B A17B |
| LMArena Text: multi-turn | 1289 | 1446 | Qwen3.5 397B A17B |
| LMArena Text: longer queries | 1280 | 1441 | Qwen3.5 397B A17B |
| LMArena Text: writing and language | 1277 | 1415 | Qwen3.5 397B A17B |
| LMArena Text: entertainment and media | 1250 | 1399 | Qwen3.5 397B A17B |
| LMArena Vision: English | 1150 | 1268 | Qwen3.5 397B A17B |
| LMArena Vision: Chinese | 1141 | 1314 | Qwen3.5 397B A17B |
| LMArena Vision: reading text | 1143 | 1271 | Qwen3.5 397B A17B |
| LMArena Vision: humor | 1100 | 1262 | Qwen3.5 397B A17B |
| LMArena Vision: captioning | Not measured | 1230 | Only Qwen3.5 397B A17B measured |
| LMArena Vision: recognizing things | Not measured | 1265 | Only Qwen3.5 397B A17B measured |
| LMArena Vision: creative writing | 1099 | 1260 | Qwen3.5 397B A17B |
| Neither model has a result on the other 15 boards here | |||
Image generationNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
| Benchmark | Llama 4 Maverick | Qwen3.5 397B A17B | 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 Maverick costs less
Repository review
50K input + 3K output tokens
Llama 4 Maverick costs less
Agent loop
200K input + 10K output tokens
Llama 4 Maverick 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 Maverick | Qwen3.5 397B A17B |
|---|---|---|
| Maker | Meta Llama | Qwen |
| Weights | Open weights | Open weights |
| Released | April 5, 2025 | February 16, 2026 |
| Context window | 524K | 262K |
| Input $/Mtok | $0.35 | $0.39 |
| Output $/Mtok | $1.00 | $2.34 |
| Coding index | Not benchmarked | Not benchmarked |
| Independent measurements behind it | 0 | 1 |
| Cost per solved task | $1.491 | Not computable |
| Source | OpenRouter listing | OpenRouter listing |
Questions
Is Llama 4 Maverick better than Qwen3.5 397B A17B for coding?
Neither model has a coding score yet, so the two cannot be ranked on coding. Pick Llama 4 Maverick for output tokens 2.3x cheaper ($1.00 vs $2.34 per million) and a larger context window (524K against 262K tokens).
Which is cheaper, Llama 4 Maverick or Qwen3.5 397B A17B?
Llama 4 Maverick costs $0.35 per million input tokens and $1.00 per million output tokens; Qwen3.5 397B A17B costs $0.39 and $2.34. Cost per solved task is known for Llama 4 Maverick only.
Which has the bigger context window, Llama 4 Maverick or Qwen3.5 397B A17B?
Llama 4 Maverick, with 524K tokens against 262K.
How many benchmarks is the Llama 4 Maverick vs Qwen3.5 397B A17B comparison based on?
54 benchmarks have a result for both models as of October 22, 2026. Llama 4 Maverick's coding index rests on 0 independent benchmarks and Qwen3.5 397B A17B's on 1. Where only one model has a result, the page says so instead of naming a winner.