As of October 20, 2026, Anthropic Claude Opus 4.6 ranks #47 of 213 models overall with 31.9 on the Artificial Analysis Intelligence Index. Its strongest category is knowledge, where it ranks #14 of 147. Anthropic Claude Opus 4.6 costs $5.00 per million input tokens and $25.00 per million output tokens. It was released on February 4, 2026.
Its output price ranks 327 of 349 priced models, counting from the cheapest.
Opus 4.6 is Anthropic’s strongest model for coding and long-running professional tasks. It is built for agents that operate across entire workflows rather than single prompts, making it especially effective...
anthropic/claude-opus-4.6 The tick on a coding bar is the median of every model measured on it. Outside coding, the place is this model's rank on that board. A board that never ran the model says so.
Measured in 5 of 6 categories. A place counts only the models measured on that board.
The index averages only the coding benchmarks that have a result; the others are skipped, never filled in. How it is weighted
Not measured on SWE-bench Lite, SWE-bench (full test set), SWE-bench Multimodal, AA Coding Index, Terminal-Bench 4 (Vals AI), Code migration (Vals AI), ProgramBench (Vals AI), IOI (Vals AI), Terminal-Bench 2.1 (Vals AI), SWE-bench Multimodal (Vals AI), Vibe Code Bench 1-100 (Vals AI), SkillsBench (Vals AI), CyberBench (Vals AI), LiveCodeBench (Artificial Analysis run), SciCode, DeepSWE, FrontierSWE, MirrorCode, ALE-Bench
Not measured on AA Agentic Index, Design Arena: agents building Godot games, Design Arena: HTML slides, Design Arena: PowerPoint slides, Design Arena: spreadsheets, LiveBench research, LiveBench browser, LiveBench long agentic, SREBench (Vals AI), Finance Agent (Vals AI), Tax Agent Bench (Vals AI), Legal Research Bench (Vals AI), Harvey's Legal Agent Benchmark (Vals AI), Excel Modeling Benchmark (Vals AI), BioMysteryBench (Vals AI), Terminal-Bench-Science (Vals AI), Vals Science Index, Time Horizon Index (Vals AI), CUA-bench (Vals AI), Robo-bench (Vals AI), GDPval, OSWorld 2.0, BALROG, PostTrainBench, TheAgentCompany, OSWorld, SpireClimb, LMArena Search
Not measured on LiveBench reasoning, MysteryMechanism (Vals AI), VPCT, BIG-Bench Hard
Not measured on MATH 500 (Vals AI), MGSM (Vals AI), AA Math Index, AIME 2025 (Artificial Analysis run), MATH level 5, GSM8K
Not measured on MMLU Pro (Artificial Analysis run), MMLU, GeoBench, AI2 Reasoning Challenge
Not measured on LiveBench design
Not measured on Vals Index, LiveBench data analysis, Public Benefits Bench (Vals AI), Vals Multimodal Index, Fiction.LiveBench, Creative writing (Lech Mazur), Surface Evolver Bench, ExploitBench, HellaSwag, WinoGrande, PIQA, LMArena Vision: captioning
Not measured on Design Arena: images, Design Arena: graphic design, Design Arena: logos, LMArena Text to Image, LMArena Image Edit
Public boards shown as published (Vals AI, Artificial Analysis, Design Arena) and kept out of the coding index. Each links to its source on the benchmark page.
| Benchmark | Result | Index weight |
|---|---|---|
| Aider polyglotCoding | Not measured | 35% |
| SWE-bench VerifiedCoding | 75.6% | 30% |
| SWE-bench LiteCoding | Not measured | Not in index |
| SWE-bench (full test set)Coding | Not measured | Not in index |
| SWE-bench MultimodalCoding | Not measured | Not in index |
| SWE-bench MultilingualCoding | 72.0% | Not in index |
| LiveBench codingCoding | Not measured | 20% |
| LMArena WebDevCoding | 1547 | 15% |
| Vals IndexGeneral | Not measured | Not in index |
| GPQA DiamondReasoning | 89.7% | Not in index |
| AIMEMath | 95.6% | Not in index |
| MMLU ProKnowledge | 89.1% | Not in index |
| AA Intelligence IndexIntelligence | 31.9 | Not in index |
| AA Coding IndexCoding | Not measured | Not in index |
| AA Agentic IndexAgentic work | Not measured | Not in index |
| Design Arena: websitesWeb design | 1291 | Not in index |
| Design Arena: UI componentsWeb design | 1285 | Not in index |
| Design Arena: game devWeb design | 1277 | Not in index |
| Design Arena: data vizWeb design | 1279 | Not in index |
| Design Arena: 3DWeb design | 1274 | Not in index |
| Design Arena: all code categoriesWeb design | 1289 | Not in index |
| Design Arena: SVGWeb design | 1227 | Not in index |
| Design Arena: ASCII artWeb design | 1255 | Not in index |
| Design Arena: agents building web appsAgentic work | 1206 | Not in index |
| Design Arena: agents building full-stack appsAgentic work | 1220 | Not in index |
| Design Arena: agents building mobile appsAgentic work | 1206 | Not in index |
| Design Arena: agents building Android appsAgentic work | 1214 | Not in index |
| Design Arena: agents building Godot gamesAgentic work | Not measured | Not in index |
| Design Arena: agents building gamesAgentic work | 1212 | Not in index |
| Design Arena: HTML slidesAgentic work | Not measured | Not in index |
| Design Arena: PowerPoint slidesAgentic work | Not measured | Not in index |
| Design Arena: spreadsheetsAgentic work | Not measured | Not in index |
| Design Arena: imagesImage generation | Not measured | Not in index |
| Design Arena: graphic designImage generation | Not measured | Not in index |
| Design Arena: logosImage generation | Not measured | Not in index |
| LiveBench reasoningReasoning | Not measured | Not in index |
| LiveBench data analysisGeneral | Not measured | Not in index |
| LiveBench researchAgentic work | Not measured | Not in index |
| LiveBench browserAgentic work | Not measured | Not in index |
| LiveBench long agenticAgentic work | Not measured | Not in index |
| LiveBench designWeb design | Not measured | Not in index |
| LiveCodeBench (Vals AI)Coding | 84.7% | Not in index |
| SWE-bench Verified (Vals AI)Coding | 78.2% | Not in index |
| Terminal-Bench 4 (Vals AI)Coding | Not measured | Not in index |
| Vibe Code Bench (Vals AI)Coding | 57.6% | Not in index |
| Code migration (Vals AI)Coding | Not measured | Not in index |
| ProgramBench (Vals AI)Coding | Not measured | Not in index |
| SREBench (Vals AI)Agentic work | Not measured | Not in index |
| IOI (Vals AI)Coding | Not measured | Not in index |
| Terminal-Bench 2.1 (Vals AI)Coding | Not measured | Not in index |
| SWE-bench Multimodal (Vals AI)Coding | Not measured | Not in index |
| Vibe Code Bench 1-100 (Vals AI)Coding | Not measured | Not in index |
| SkillsBench (Vals AI)Coding | Not measured | Not in index |
| CyberBench (Vals AI)Coding | Not measured | Not in index |
| Finance Agent (Vals AI)Agentic work | Not measured | Not in index |
| Tax Agent Bench (Vals AI)Agentic work | Not measured | Not in index |
| Legal Research Bench (Vals AI)Agentic work | Not measured | Not in index |
| Harvey's Legal Agent Benchmark (Vals AI)Agentic work | Not measured | Not in index |
| Excel Modeling Benchmark (Vals AI)Agentic work | Not measured | Not in index |
| BioMysteryBench (Vals AI)Agentic work | Not measured | Not in index |
| Terminal-Bench-Science (Vals AI)Agentic work | Not measured | Not in index |
| Vals Science IndexAgentic work | Not measured | Not in index |
| Time Horizon Index (Vals AI)Agentic work | Not measured | Not in index |
| CUA-bench (Vals AI)Agentic work | Not measured | Not in index |
| Robo-bench (Vals AI)Agentic work | Not measured | Not in index |
| Public Benefits Bench (Vals AI)General | Not measured | Not in index |
| MysteryMechanism (Vals AI)Reasoning | Not measured | Not in index |
| MMMU Pro (Vals AI)Reasoning | 83.9% | Not in index |
| MATH 500 (Vals AI)Math | Not measured | Not in index |
| MGSM (Vals AI)Math | Not measured | Not in index |
| SAGE (Vals AI)General | 51.6% | Not in index |
| LegalBench (Vals AI)Knowledge | 85.3% | Not in index |
| CaseLaw (Vals AI)Knowledge | 62.1% | Not in index |
| CorpFin (Vals AI)Knowledge | 67.0% | Not in index |
| TaxEval (Vals AI)Knowledge | 76.0% | Not in index |
| MortgageTax (Vals AI)Knowledge | 68.5% | Not in index |
| MedQA (Vals AI)Knowledge | 95.4% | Not in index |
| MedCode (Vals AI)Knowledge | 49.1% | Not in index |
| MedScribe (Vals AI)General | 86.7% | Not in index |
| Vals Multimodal IndexGeneral | Not measured | Not in index |
| AA Math IndexMath | Not measured | Not in index |
| GPQA Diamond (Artificial Analysis run)Reasoning | 89.6% | Not in index |
| Humanity's Last Exam (Artificial Analysis run)Reasoning | 39.9% | Not in index |
| MMLU Pro (Artificial Analysis run)Knowledge | Not measured | Not in index |
| LiveCodeBench (Artificial Analysis run)Coding | Not measured | Not in index |
| SciCodeCoding | Not measured | Not in index |
| Terminal-Bench Hard (Artificial Analysis run)Coding | 48.5% | Not in index |
| IFBenchGeneral | 53.1% | Not in index |
| Long context reasoning (AA-LCR)General | 78.0% | Not in index |
| τ²-Bench TelecomAgentic work | 92.1% | Not in index |
| AIME 2025 (Artificial Analysis run)Math | Not measured | Not in index |
| Terminal-BenchCoding | 79.8% | Not in index |
| DeepSWECoding | Not measured | Not in index |
| FrontierCodeCoding | 26.6% | Not in index |
| FrontierSWECoding | Not measured | Not in index |
| GSO-BenchCoding | 41.2% | Not in index |
| WeirdMLCoding | 78.0% | Not in index |
| MirrorCodeCoding | Not measured | Not in index |
| APEX-AgentsAgentic work | 46.3% | Not in index |
| METR time horizonsAgentic work | 78.9% | Not in index |
| Remote Labor IndexAgentic work | 4.2% | Not in index |
| GDPvalAgentic work | Not measured | Not in index |
| OSWorld 2.0Agentic work | Not measured | Not in index |
| BALROGAgentic work | Not measured | Not in index |
| DeepResearch BenchAgentic work | 55.3% | Not in index |
| PostTrainBenchAgentic work | Not measured | Not in index |
| GPQA Diamond (Epoch AI run)Reasoning | 90.5% | Not in index |
| ARC-AGIReasoning | 94.0% | Not in index |
| ARC-AGI-2Reasoning | 69.2% | Not in index |
| Humanity's Last ExamReasoning | 34.4% | Not in index |
| SimpleBenchReasoning | 67.6% | Not in index |
| Chess puzzlesReasoning | 21.0% | Not in index |
| Mystery game puzzlesReasoning | 25.0% | Not in index |
| EBR-benchReasoning | 12.7% | Not in index |
| OTIS Mock AIMEMath | 94.4% | Not in index |
| FrontierMath, tiers 1 to 3Math | 66.0% | Not in index |
| FrontierMath, tier 4Math | 26.8% | Not in index |
| ProofBenchMath | 50.0% | Not in index |
| MATH level 5Math | Not measured | Not in index |
| GSM8KMath | Not measured | Not in index |
| SimpleQA VerifiedKnowledge | 47.0% | Not in index |
| MMLUKnowledge | Not measured | Not in index |
| GeoBenchKnowledge | Not measured | Not in index |
| DTBenchGeneral | 91.2% | Not in index |
| LMCAGeneral | 55.8% | Not in index |
| Fiction.LiveBenchGeneral | Not measured | Not in index |
| Creative writing (Lech Mazur)General | Not measured | Not in index |
| CL-benchGeneral | 20.7% | Not in index |
| Surface Evolver BenchGeneral | Not measured | Not in index |
| Furniture assemblyGeneral | 28.3% | Not in index |
| ExploitBenchGeneral | Not measured | Not in index |
| CybenchCoding | 93.0% | Not in index |
| TheAgentCompanyAgentic work | Not measured | Not in index |
| OSWorldAgentic work | Not measured | Not in index |
| SpireClimbAgentic work | Not measured | Not in index |
| VPCTReasoning | Not measured | Not in index |
| BIG-Bench HardReasoning | Not measured | Not in index |
| AI2 Reasoning ChallengeKnowledge | Not measured | Not in index |
| HellaSwagGeneral | Not measured | Not in index |
| WinoGrandeGeneral | Not measured | Not in index |
| PIQAGeneral | Not measured | Not in index |
| CL-bench LifeGeneral | 17.0% | Not in index |
| ALE-BenchCoding | Not measured | Not in index |
| Vending-Bench 2Agentic work | $8,018 | Not in index |
| Epoch Capabilities IndexIntelligence | 155.3 | Not in index |
| LMArena TextGeneral | 1502 | Not in index |
| LMArena Text: codingCoding | 1535 | Not in index |
| LMArena Text: hard promptsReasoning | 1525 | Not in index |
| LMArena Text: mathMath | 1519 | Not in index |
| LMArena Text: instruction followingGeneral | 1522 | Not in index |
| LMArena Text: creative writingGeneral | 1505 | Not in index |
| LMArena VisionGeneral | 1316 | Not in index |
| LMArena Text: EnglishGeneral | 1512 | Not in index |
| LMArena Text: non-EnglishGeneral | 1488 | Not in index |
| LMArena Text: ChineseGeneral | 1550 | Not in index |
| LMArena Text: GermanGeneral | 1502 | Not in index |
| LMArena Text: JapaneseGeneral | 1488 | Not in index |
| LMArena Text: KoreanGeneral | 1465 | Not in index |
| LMArena Text: FrenchGeneral | 1513 | Not in index |
| LMArena Text: SpanishGeneral | 1510 | Not in index |
| LMArena Text: RussianGeneral | 1496 | Not in index |
| LMArena Text: PolishGeneral | 1497 | Not in index |
| LMArena Text: multi-turnGeneral | 1512 | Not in index |
| LMArena Text: longer queriesGeneral | 1518 | Not in index |
| LMArena Text: expertReasoning | 1545 | Not in index |
| LMArena Text: hard prompts in EnglishReasoning | 1531 | Not in index |
| LMArena Text: software and ITCoding | 1528 | Not in index |
| LMArena Text: mathematical workMath | 1526 | Not in index |
| LMArena Text: scienceKnowledge | 1520 | Not in index |
| LMArena Text: medicine and healthcareKnowledge | 1505 | Not in index |
| LMArena Text: legal and governmentKnowledge | 1512 | Not in index |
| LMArena Text: business and financeKnowledge | 1498 | Not in index |
| LMArena Text: writing and languageGeneral | 1503 | Not in index |
| LMArena Text: entertainment and mediaGeneral | 1492 | Not in index |
| LMArena WebDev: ReactCoding | 1539 | Not in index |
| LMArena WebDev: HTMLCoding | 1559 | Not in index |
| LMArena WebDev: from an imageCoding | 1543 | Not in index |
| LMArena Vision: EnglishGeneral | 1324 | Not in index |
| LMArena Vision: ChineseGeneral | 1370 | Not in index |
| LMArena Vision: reading textGeneral | 1326 | Not in index |
| LMArena Vision: diagramsReasoning | 1340 | Not in index |
| LMArena Vision: homeworkReasoning | 1337 | Not in index |
| LMArena Vision: humorGeneral | 1314 | Not in index |
| LMArena Vision: captioningGeneral | Not measured | Not in index |
| LMArena Vision: recognizing thingsGeneral | 1274 | Not in index |
| LMArena Vision: creative writingGeneral | 1331 | Not in index |
| LMArena SearchAgentic work | Not measured | Not in index |
| LMArena DocumentGeneral | 1507 | Not in index |
| LMArena Text to ImageImage generation | Not measured | Not in index |
| LMArena Image EditImage generation | Not measured | Not in index |
A list price says what a token costs. The cost per solved task says what a working answer costs, which is the number that decides.
Beside a result, many boards publish what the run cost, how long it took, the tokens it spent or the votes behind a rating. Each figure as its board printed it, one board per row.
| Board | Result | What the run cost | Also published |
|---|---|---|---|
| SWE-bench Verified | 75.6% | $0.5515 per attempt | Nothing else |
| SWE-bench Multilingual | 72.0% | $0.663 per attempt | Nothing else |
| SWE-bench Verified (Vals AI) | 78.2% | $1.22 per test | Duration, as printed 5m 51s |
| Vibe Code Bench (Vals AI) | 57.6% | $8.69 per test | Duration, as printed 21m 19s |
| WeirdML | 78.0% | $5.7794 per run | Median lines of code 169 |
| ProofBench | 50.0% | $2.7036 per test | Time per proof 1h 06m |
| LMArena WebDev | 1547 Elo | Not published | Votes 19,383 · Interval (±) ±5.5 |
| GPQA Diamond | 89.7% | Not published | Latency, as printed 5m 19s |
| AIME | 95.6% | Not published | Latency, as printed 4m 56s |
| MMLU Pro | 89.1% | Not published | Latency, as printed 49 s |
| Design Arena: websites | 1291 Elo | Not published | Battles 14,720 |
| Design Arena: UI components | 1285 Elo | Not published | Battles 2,319 |
| Design Arena: game dev | 1277 Elo | Not published | Battles 2,745 |
|---|---|---|---|
| Design Arena: data viz | 1279 Elo | Not published | Battles 1,919 |
| Design Arena: 3D | 1274 Elo | Not published | Battles 5,862 |
| Design Arena: all code categories | 1289 Elo | Not published | Battles 27,406 |
| Design Arena: SVG | 1227 Elo | Not published | Battles 3,987 |
| Design Arena: ASCII art | 1255 Elo | Not published | Battles 412 |
| Design Arena: agents building web apps | 1206 Elo | Not published | Battles 4,135 |
| Design Arena: agents building full-stack apps | 1220 Elo | Not published | Battles 2,517 |
| Design Arena: agents building mobile apps | 1206 Elo | Not published | Battles 2,143 |
| Design Arena: agents building Android apps | 1214 Elo | Not published | Battles 778 |
| Design Arena: agents building games | 1212 Elo | Not published | Battles 219 |
| LiveCodeBench (Vals AI) | 84.7% | Not published | Latency, as printed 5m 24s |
| MMMU Pro (Vals AI) | 83.9% | Not published | Latency, as printed 1m 59s |
| SAGE (Vals AI) | 51.6% | Not published | Latency, as printed 2m 41s |
| LegalBench (Vals AI) | 85.3% | Not published | Latency, as printed 3.8 s |
| CaseLaw (Vals AI) | 62.1% | Not published | Latency, as printed 32 s |
| CorpFin (Vals AI) | 67.0% | Not published | Latency, as printed 21 s |
| TaxEval (Vals AI) | 76.0% | Not published | Latency, as printed 1m 19s |
| MortgageTax (Vals AI) | 68.5% | Not published | Latency, as printed 27 s |
| MedQA (Vals AI) | 95.4% | Not published | Latency, as printed 30 s |
| MedCode (Vals AI) | 49.1% | Not published | Latency, as printed 2m 36s |
| MedScribe (Vals AI) | 86.7% | Not published | Latency, as printed 54 s |
| APEX-Agents | 46.3% | Not published | Mean score 61.8% |
| LMArena Text | 1502 Elo | Not published | Votes 81,394 · Interval (±) ±3.3 |
| LMArena Text: coding | 1535 Elo | Not published | Votes 23,838 · Interval (±) ±5.1 |
| LMArena Text: hard prompts | 1525 Elo | Not published | Votes 51,834 · Interval (±) ±4.0 |
| LMArena Text: math | 1519 Elo | Not published | Votes 4,186 · Interval (±) ±9.6 |
| LMArena Text: instruction following | 1522 Elo | Not published | Votes 26,220 · Interval (±) ±5.0 |
| LMArena Text: creative writing | 1505 Elo | Not published | Votes 14,950 · Interval (±) ±6.2 |
| LMArena Vision | 1316 Elo | Not published | Votes 22,286 · Interval (±) ±6.4 |
| LMArena Text: English | 1512 Elo | Not published | Votes 35,808 · Interval (±) ±4.4 |
| LMArena Text: non-English | 1488 Elo | Not published | Votes 45,580 · Interval (±) ±4.0 |
| LMArena Text: Chinese | 1550 Elo | Not published | Votes 5,649 · Interval (±) ±8.8 |
| LMArena Text: German | 1502 Elo | Not published | Votes 1,292 · Interval (±) ±17.4 |
| LMArena Text: Japanese | 1488 Elo | Not published | Votes 930 · Interval (±) ±21.3 |
| LMArena Text: Korean | 1465 Elo | Not published | Votes 1,541 · Interval (±) ±16.8 |
| LMArena Text: French | 1513 Elo | Not published | Votes 2,652 · Interval (±) ±13.3 |
| LMArena Text: Spanish | 1510 Elo | Not published | Votes 2,844 · Interval (±) ±12.4 |
| LMArena Text: Russian | 1496 Elo | Not published | Votes 9,363 · Interval (±) ±6.9 |
| LMArena Text: Polish | 1497 Elo | Not published | Votes 1,535 · Interval (±) ±15.3 |
| LMArena Text: multi-turn | 1512 Elo | Not published | Votes 13,816 · Interval (±) ±6.2 |
| LMArena Text: longer queries | 1518 Elo | Not published | Votes 34,498 · Interval (±) ±4.8 |
| LMArena Text: expert | 1545 Elo | Not published | Votes 7,403 · Interval (±) ±7.8 |
| LMArena Text: hard prompts in English | 1531 Elo | Not published | Votes 23,259 · Interval (±) ±5.2 |
| LMArena Text: software and IT | 1528 Elo | Not published | Votes 33,580 · Interval (±) ±4.5 |
| LMArena Text: mathematical work | 1526 Elo | Not published | Votes 4,247 · Interval (±) ±9.9 |
| LMArena Text: science | 1520 Elo | Not published | Votes 13,562 · Interval (±) ±6.1 |
| LMArena Text: medicine and healthcare | 1505 Elo | Not published | Votes 6,131 · Interval (±) ±8.4 |
| LMArena Text: legal and government | 1512 Elo | Not published | Votes 6,644 · Interval (±) ±8.1 |
| LMArena Text: business and finance | 1498 Elo | Not published | Votes 15,952 · Interval (±) ±5.8 |
| LMArena Text: writing and language | 1503 Elo | Not published | Votes 21,041 · Interval (±) ±5.3 |
| LMArena Text: entertainment and media | 1492 Elo | Not published | Votes 18,420 · Interval (±) ±5.7 |
| LMArena WebDev: React | 1539 Elo | Not published | Votes 15,128 · Interval (±) ±6.1 |
| LMArena WebDev: HTML | 1559 Elo | Not published | Votes 2,462 · Interval (±) ±13.3 |
| LMArena WebDev: from an image | 1543 Elo | Not published | Votes 7,938 · Interval (±) ±8.9 |
| LMArena Vision: English | 1324 Elo | Not published | Votes 9,235 · Interval (±) ±8.7 |
| LMArena Vision: Chinese | 1370 Elo | Not published | Votes 1,681 · Interval (±) ±17.1 |
| LMArena Vision: reading text | 1326 Elo | Not published | Votes 19,407 · Interval (±) ±6.3 |
| LMArena Vision: diagrams | 1340 Elo | Not published | Votes 7,249 · Interval (±) ±8.7 |
| LMArena Vision: homework | 1337 Elo | Not published | Votes 2,845 · Interval (±) ±11.9 |
| LMArena Vision: humor | 1314 Elo | Not published | Votes 1,026 · Interval (±) ±19.4 |
| LMArena Vision: recognizing things | 1274 Elo | Not published | Votes 189 · Interval (±) ±38.4 |
| LMArena Vision: creative writing | 1331 Elo | Not published | Votes 1,407 · Interval (±) ±16.8 |
| LMArena Document | 1507 Elo | Not published | Votes 27,929 · Interval (±) ±6.4 |