Claude Opus 4.5 vs Llama 4 Maverick
Claude Opus 4.5 leads Llama 4 Maverick on the Artificial Analysis Intelligence Index, 29.1 to 9.3, and Llama 4 Maverick costs 25.0x less per output token ($1.00 vs $25.00 per million). Updated October 22, 2026; 69 benchmarks have a result for both.
Claude Opus 4.5 or Llama 4 Maverick: which to pick
Only Claude Opus 4.5 has a coding score, 44.0 on the Vibe Coding Index; Llama 4 Maverick has none, so the two cannot be ranked on coding.
Pick Llama 4 Maverick for output tokens 25.0x cheaper ($1.00 vs $25.00 per million) and a larger context window (524K against 200K tokens).
- Shared results
- 69
- Claude Opus 4.5 only
- 39
- Llama 4 Maverick only
- 16
- 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
Only Claude Opus 4.5 has a coding score, so no call is made.
One side not measured
Intelligence
AA Intelligence Index
Claude Opus 4.5
Claude Opus 4.5 leads, 29.1 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
Claude Opus 4.5
Claude Opus 4.5 leads, 85.9% against 69.4%.
Same board, both measured
Math
AIME
Claude Opus 4.5
Claude Opus 4.5 leads, 95.4% against 25.2%.
Same board, both measured
Knowledge
MMLU Pro
Claude Opus 4.5
Claude Opus 4.5 leads, 87.3% against 79.4%.
Same board, both measured
Web design
Design Arena: websites
Claude Opus 4.5
Claude Opus 4.5 leads, 1247 against 871.
Same board, both measured
Long documents
Listed context window
Llama 4 Maverick
Llama 4 Maverick takes 524K tokens against 200K.
Listed by OpenRouter
Everyday cost
1K input + 500 output tokens
Llama 4 Maverick
Claude Opus 4.5 $0.018, Llama 4 Maverick $0.0008 per turn.
List prices
Cost per solved task
One SWE-bench Verified task, solved
Claude Opus 4.5
Claude Opus 4.5 $1.37, Llama 4 Maverick $1.491.
Published attempt cost and pass rate
At a glance
- Coding index
- Claude Opus 4.5 44.0 from 3 benchmarks, Llama 4 Maverick not benchmarked.
- Widest category
- Agentic work, 71.6 points apart on average over 1 shared benchmark.
- Widest single gap
- ARC-AGI: Claude Opus 4.5 80.0% against Llama 4 Maverick 4.4%, 75.6 points apart on a 0 to 100 scale.
- Output price
- Claude Opus 4.5 $25.00 against Llama 4 Maverick $1.00 per million output tokens, 25.0x apart.
- Context window
- Claude Opus 4.5 takes 200K tokens, Llama 4 Maverick 524K.
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 | Claude Opus 4.5 | Bars | Llama 4 Maverick | Ties |
|---|---|---|---|---|
| Coding | 7 | 0 | ||
| Intelligence | 2 | 0 | ||
| Agentic work | 1 | 0 | ||
| Reasoning | 11 | 0 | ||
| Math | 6 | 0 | ||
| Knowledge | 13 | 0 | ||
| Web design | 6 | 0 | ||
| General | 23 | 0 | ||
| All shared boards | 69 | 0 |
CodingLike-for-likeSix of these boards feed the Vibe Coding Index70
| Benchmark | Claude Opus 4.5 | Llama 4 Maverick | Leader |
|---|---|---|---|
| Aider polyglot | Not measured | 15.6% | Only Llama 4 Maverick measured |
| SWE-bench Verified | 79.2% | 21.0% | Claude Opus 4.5 |
| SWE-bench (full test set) | 52.6% | Not measured | Only Claude Opus 4.5 measured |
| SWE-bench Multilingual | 70.7% | Not measured | Only Claude Opus 4.5 measured |
| LMArena WebDev | 1494 | Not measured | Only Claude Opus 4.5 measured |
| AA Coding Index | Not measured | 16.3 | Only Llama 4 Maverick measured |
| LiveCodeBench (Vals AI) | 83.7% | 47.3% | Claude Opus 4.5 |
| SWE-bench Verified (Vals AI) | 76.4% | Not measured | Only Claude Opus 4.5 measured |
| Vibe Code Bench (Vals AI) | 20.6% | Not measured | Only Claude Opus 4.5 measured |
| LiveCodeBench (Artificial Analysis run) | 87.1% | 39.7% | Claude Opus 4.5 |
| SciCode | Not measured | 31.7% | Only Llama 4 Maverick measured |
| Terminal-Bench Hard (Artificial Analysis run) | 47.0% | 6.8% | Claude Opus 4.5 |
| Terminal-Bench | 63.1% | Not measured | Only Claude Opus 4.5 measured |
| GSO-Bench | 26.5% | Not measured | Only Claude Opus 4.5 measured |
| WeirdML | 63.7% | 24.5% | Claude Opus 4.5 |
| Cybench | 82.0% | Not measured | Only Claude Opus 4.5 measured |
| ALE-Bench | Not measured | 173.0 | Only Llama 4 Maverick measured |
| LMArena Text: coding | 1503 | 1301 | Claude Opus 4.5 |
| LMArena Text: software and IT | 1483 | 1299 | Claude Opus 4.5 |
| LMArena WebDev: React | 1478 | Not measured | Only Claude Opus 4.5 measured |
| LMArena WebDev: HTML | 1510 | Not measured | Only Claude Opus 4.5 measured |
| Neither model has a result on the other 18 boards here | |||
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index20
| Benchmark | Claude Opus 4.5 | Llama 4 Maverick | Leader |
|---|---|---|---|
| AA Intelligence Index | 29.1 | 9.3 | Claude Opus 4.5 |
| Epoch Capabilities Index | 150.1 | 132.2 | Claude Opus 4.5 |
Agentic workLike-for-likePublic boards, shown as published, kept out of the index10
| Benchmark | Claude Opus 4.5 | Llama 4 Maverick | Leader |
|---|---|---|---|
| AA Agentic Index | Not measured | 0.6 | Only Llama 4 Maverick measured |
| Design Arena: agents building web apps | 1159 | Not measured | Only Claude Opus 4.5 measured |
| Design Arena: agents building full-stack apps | 1156 | Not measured | Only Claude Opus 4.5 measured |
| Design Arena: agents building mobile apps | 1189 | Not measured | Only Claude Opus 4.5 measured |
| Design Arena: agents building Android apps | 1176 | Not measured | Only Claude Opus 4.5 measured |
| τ²-Bench Telecom | 89.5% | 17.8% | Claude Opus 4.5 |
| METR time horizons | 75.0% | Not measured | Only Claude Opus 4.5 measured |
| Remote Labor Index | 3.8% | Not measured | Only Claude Opus 4.5 measured |
| GDPval | 45.5% | Not measured | Only Claude Opus 4.5 measured |
| BALROG | 43.5% | Not measured | Only Claude Opus 4.5 measured |
| DeepResearch Bench | 54.8% | Not measured | Only Claude Opus 4.5 measured |
| OSWorld | 66.3% | Not measured | Only Claude Opus 4.5 measured |
| Vending-Bench 2 | $4,967 | Not measured | Only Claude Opus 4.5 measured |
| Berkeley Function Calling Leaderboard (BFCL) | 77.5% | Not measured | Only Claude Opus 4.5 measured |
| Neither model has a result on the other 27 boards here | |||
ReasoningLike-for-likePublic boards, shown as published, kept out of the index110
| Benchmark | Claude Opus 4.5 | Llama 4 Maverick | Leader |
|---|---|---|---|
| GPQA Diamond | 85.9% | 69.4% | Claude Opus 4.5 |
| MMMU Pro (Vals AI) | 83.0% | 71.7% | Claude Opus 4.5 |
| GPQA Diamond (Artificial Analysis run) | 86.6% | 67.1% | Claude Opus 4.5 |
| Humanity's Last Exam (Artificial Analysis run) | 30.1% | 4.9% | Claude Opus 4.5 |
| GPQA Diamond (Epoch AI run) | 86.0% | Not measured | Only Claude Opus 4.5 measured |
| ARC-AGI | 80.0% | 4.4% | Claude Opus 4.5 |
| ARC-AGI-2 | 37.6% | 0.0% | Claude Opus 4.5 |
| SimpleBench | 62.0% | 27.7% | Claude Opus 4.5 |
| Chess puzzles | 14.0% | Not measured | Only Claude Opus 4.5 measured |
| Mystery game puzzles | 22.0% | Not measured | Only Claude Opus 4.5 measured |
| EBR-bench | 14.3% | Not measured | Only Claude Opus 4.5 measured |
| VPCT | 40.0% | Not measured | Only Claude Opus 4.5 measured |
| LMArena Text: hard prompts | 1476 | 1281 | Claude Opus 4.5 |
| LMArena Text: expert | 1487 | 1259 | Claude Opus 4.5 |
| LMArena Text: hard prompts in English | 1482 | 1295 | Claude Opus 4.5 |
| LMArena Vision: diagrams | Not measured | 1134 | Only Llama 4 Maverick measured |
| LMArena Vision: homework | Not measured | 1164 | Only Llama 4 Maverick measured |
| Kagi LLM Benchmark | 80.2% | 55.9% | Claude Opus 4.5 |
| Neither model has a result on the other 4 boards here | |||
MathLike-for-likePublic boards, shown as published, kept out of the index60
| Benchmark | Claude Opus 4.5 | Llama 4 Maverick | Leader |
|---|---|---|---|
| AIME | 95.4% | 25.2% | Claude Opus 4.5 |
| MATH 500 (Vals AI) | Not measured | 85.2% | Only Llama 4 Maverick measured |
| MGSM (Vals AI) | 95.2% | 92.4% | Claude Opus 4.5 |
| AA Math Index | 91.3 | 19.3 | Claude Opus 4.5 |
| AIME 2025 (Artificial Analysis run) | 91.3% | 19.3% | Claude Opus 4.5 |
| OTIS Mock AIME | 86.1% | Not measured | Only Claude Opus 4.5 measured |
| FrontierMath, tiers 1 to 3 | 34.4% | Not measured | Only Claude Opus 4.5 measured |
| FrontierMath, tier 4 | 4.9% | Not measured | Only Claude Opus 4.5 measured |
| ProofBench | 36.0% | Not measured | Only Claude Opus 4.5 measured |
| LMArena Text: math | 1463 | 1299 | Claude Opus 4.5 |
| LMArena Text: mathematical work | 1468 | 1295 | Claude Opus 4.5 |
| Neither model has a result on the other 2 boards here | |||
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index130
| Benchmark | Claude Opus 4.5 | Llama 4 Maverick | Leader |
|---|---|---|---|
| MMLU Pro | 87.3% | 79.4% | Claude Opus 4.5 |
| LegalBench (Vals AI) | 84.6% | 77.8% | Claude Opus 4.5 |
| CaseLaw (Vals AI) | 62.6% | Not measured | Only Claude Opus 4.5 measured |
| CorpFin (Vals AI) | 65.1% | 49.7% | Claude Opus 4.5 |
| TaxEval (Vals AI) | 74.9% | 66.6% | Claude Opus 4.5 |
| MortgageTax (Vals AI) | 68.7% | 58.5% | Claude Opus 4.5 |
| MedQA (Vals AI) | 95.9% | 43.3% | Claude Opus 4.5 |
| MedCode (Vals AI) | 49.2% | 36.5% | Claude Opus 4.5 |
| MMLU Pro (Artificial Analysis run) | 89.5% | 80.9% | Claude Opus 4.5 |
| SimpleQA Verified | 45.7% | Not measured | Only Claude Opus 4.5 measured |
| GeoBench | 75.0% | 52.0% | Claude Opus 4.5 |
| LMArena Text: science | 1454 | 1288 | Claude Opus 4.5 |
| LMArena Text: medicine and healthcare | 1444 | 1275 | Claude Opus 4.5 |
| LMArena Text: legal and government | 1459 | 1286 | Claude Opus 4.5 |
| LMArena Text: business and finance | 1448 | 1260 | Claude Opus 4.5 |
| FACTS Benchmark Suite | 43.9% | Not measured | Only Claude Opus 4.5 measured |
| Neither model has a result on the other 2 boards here | |||
Web designLike-for-likePublic boards, shown as published, kept out of the index60
| Benchmark | Claude Opus 4.5 | Llama 4 Maverick | Leader |
|---|---|---|---|
| Design Arena: websites | 1247 | 871 | Claude Opus 4.5 |
| Design Arena: UI components | 1235 | 896 | Claude Opus 4.5 |
| Design Arena: game dev | 1228 | 837 | Claude Opus 4.5 |
| Design Arena: data viz | 1243 | 882 | Claude Opus 4.5 |
| Design Arena: 3D | 1213 | 900 | Claude Opus 4.5 |
| Design Arena: all code categories | 1242 | 879 | Claude Opus 4.5 |
| Design Arena: SVG | 1180 | Not measured | Only Claude Opus 4.5 measured |
| Design Arena: ASCII art | 1190 | Not measured | Only Claude Opus 4.5 measured |
| Neither model has a result on the other 1 board here | |||
GeneralLike-for-likePublic boards, shown as published, kept out of the index230
| Benchmark | Claude Opus 4.5 | Llama 4 Maverick | Leader |
|---|---|---|---|
| SAGE (Vals AI) | 52.1% | 35.7% | Claude Opus 4.5 |
| MedScribe (Vals AI) | 85.3% | 54.2% | Claude Opus 4.5 |
| IFBench | 58.0% | 43.0% | Claude Opus 4.5 |
| Long context reasoning (AA-LCR) | 77.3% | 50.0% | Claude Opus 4.5 |
| DTBench | 89.9% | 61.9% | Claude Opus 4.5 |
| LMCA | 44.5% | 15.9% | Claude Opus 4.5 |
| Fiction.LiveBench | Not measured | 46.2% | Only Llama 4 Maverick measured |
| Creative writing (Lech Mazur) | Not measured | 62.0% | Only Llama 4 Maverick measured |
| CL-bench | 21.1% | Not measured | Only Claude Opus 4.5 measured |
| Furniture assembly | 28.3% | Not measured | Only Claude Opus 4.5 measured |
| LMArena Text | 1451 | 1287 | Claude Opus 4.5 |
| LMArena Text: instruction following | 1478 | 1267 | Claude Opus 4.5 |
| LMArena Text: creative writing | 1445 | 1266 | Claude Opus 4.5 |
| LMArena Vision | Not measured | 1142 | Only Llama 4 Maverick measured |
| LMArena Text: English | 1461 | 1303 | Claude Opus 4.5 |
| LMArena Text: non-English | 1438 | 1269 | Claude Opus 4.5 |
| LMArena Text: Chinese | 1470 | 1277 | Claude Opus 4.5 |
| LMArena Text: German | 1449 | 1291 | Claude Opus 4.5 |
| LMArena Text: Japanese | 1417 | 1206 | Claude Opus 4.5 |
| LMArena Text: Korean | 1424 | 1203 | Claude Opus 4.5 |
| LMArena Text: French | 1471 | 1259 | Claude Opus 4.5 |
| LMArena Text: Spanish | 1457 | 1293 | Claude Opus 4.5 |
| LMArena Text: Russian | 1447 | 1286 | Claude Opus 4.5 |
| LMArena Text: Polish | 1439 | 1275 | Claude Opus 4.5 |
| LMArena Text: multi-turn | 1466 | 1289 | Claude Opus 4.5 |
| LMArena Text: longer queries | 1479 | 1280 | Claude Opus 4.5 |
| LMArena Text: writing and language | 1452 | 1277 | Claude Opus 4.5 |
| LMArena Text: entertainment and media | 1434 | 1250 | Claude Opus 4.5 |
| LMArena Vision: English | Not measured | 1150 | Only Llama 4 Maverick measured |
| LMArena Vision: Chinese | Not measured | 1141 | Only Llama 4 Maverick measured |
| LMArena Vision: reading text | Not measured | 1143 | Only Llama 4 Maverick measured |
| LMArena Vision: humor | Not measured | 1100 | Only Llama 4 Maverick measured |
| LMArena Vision: creative writing | Not measured | 1099 | Only Llama 4 Maverick measured |
| LMArena Document | 1462 | Not measured | Only Claude Opus 4.5 measured |
| Neither model has a result on the other 12 boards here | |||
Image generationNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
| Benchmark | Claude Opus 4.5 | Llama 4 Maverick | 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 | Anthropic Claude Opus 4.5 | Meta Llama 4 Maverick |
|---|---|---|
| Maker | Anthropic | Meta Llama |
| Weights | No public weights listed | Open weights |
| Released | November 24, 2025 | April 5, 2025 |
| Context window | 200K | 524K |
| Input $/Mtok | $5.00 | $0.35 |
| Output $/Mtok | $25.00 | $1.00 |
| Coding index | 44.0 | Not benchmarked |
| Independent measurements behind it | 3 | 0 |
| Cost per solved task | $1.37 | $1.491 |
| Source | OpenRouter listing | OpenRouter listing |
Questions
Is Claude Opus 4.5 better than Llama 4 Maverick for coding?
Only Claude Opus 4.5 has a coding score, 44.0 on the Vibe Coding Index; Llama 4 Maverick has none, so the two cannot be ranked on coding. Pick Llama 4 Maverick for output tokens 25.0x cheaper ($1.00 vs $25.00 per million) and a larger context window (524K against 200K tokens).
Which is cheaper, Claude Opus 4.5 or Llama 4 Maverick?
Claude Opus 4.5 costs $5.00 per million input tokens and $25.00 per million output tokens; Llama 4 Maverick costs $0.35 and $1.00. Per solved SWE-bench Verified task, Claude Opus 4.5 costs $1.37 and Llama 4 Maverick $1.491.
Which has the bigger context window, Claude Opus 4.5 or Llama 4 Maverick?
Llama 4 Maverick, with 524K tokens against 200K.
How many benchmarks is the Claude Opus 4.5 vs Llama 4 Maverick comparison based on?
69 benchmarks have a result for both models as of October 22, 2026. Claude Opus 4.5's coding index rests on 3 independent benchmarks and Llama 4 Maverick's on 0. Where only one model has a result, the page says so instead of naming a winner.