As of October 20, 2026, Anthropic Claude Opus 4.5 ranks #54 of 213 models overall with 29.1 on the Artificial Analysis Intelligence Index. Its strongest category is knowledge, where it ranks #29 of 147. Anthropic Claude Opus 4.5 costs $5.00 per million input tokens and $25.00 per million output tokens. It was released on November 24, 2025.
Its output price ranks 327 of 349 priced models, counting from the cheapest.
Claude Opus 4.5 is Anthropic’s frontier reasoning model optimized for complex software engineering, agentic workflows, and long-horizon computer use. It offers strong multimodal capabilities, competitive performance across real-world coding and...
anthropic/claude-opus-4.5 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 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), SciCode, DeepSWE, FrontierCode, FrontierSWE, MirrorCode, ALE-Bench, LMArena WebDev: from an image
Not measured on AA Agentic Index, Design Arena: agents building Godot games, Design Arena: agents building 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), APEX-Agents, OSWorld 2.0, PostTrainBench, TheAgentCompany, SpireClimb, LMArena Search
Not measured on LiveBench reasoning, MysteryMechanism (Vals AI), BIG-Bench Hard, LMArena Vision: diagrams, LMArena Vision: homework
Not measured on MATH 500 (Vals AI), MATH level 5, GSM8K
Not measured on MMLU, 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, CL-bench Life, LMArena Vision, LMArena Vision: English, LMArena Vision: Chinese, LMArena Vision: reading text, LMArena Vision: humor, LMArena Vision: captioning, LMArena Vision: recognizing things, LMArena Vision: creative writing
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 | 79.2% | 30% |
| SWE-bench LiteCoding | Not measured | Not in index |
| SWE-bench (full test set)Coding | 52.6% | Not in index |
| SWE-bench MultimodalCoding | Not measured | Not in index |
| SWE-bench MultilingualCoding | 70.7% | Not in index |
| LiveBench codingCoding | Not measured | 20% |
| LMArena WebDevCoding | 1494 | 15% |
| Vals IndexGeneral | Not measured | Not in index |
| GPQA DiamondReasoning | 85.9% | Not in index |
| AIMEMath | 95.4% | Not in index |
| MMLU ProKnowledge | 87.3% | Not in index |
| AA Intelligence IndexIntelligence | 29.1 | Not in index |
| AA Coding IndexCoding | Not measured | Not in index |
| AA Agentic IndexAgentic work | Not measured | Not in index |
| Design Arena: websitesWeb design | 1247 | Not in index |
| Design Arena: UI componentsWeb design | 1239 | Not in index |
| Design Arena: game devWeb design | 1229 | Not in index |
| Design Arena: data vizWeb design | 1243 | Not in index |
| Design Arena: 3DWeb design | 1214 | Not in index |
| Design Arena: all code categoriesWeb design | 1242 | Not in index |
| Design Arena: SVGWeb design | 1180 | Not in index |
| Design Arena: ASCII artWeb design | 1190 | Not in index |
| Design Arena: agents building web appsAgentic work | 1159 | Not in index |
| Design Arena: agents building full-stack appsAgentic work | 1156 | Not in index |
| Design Arena: agents building mobile appsAgentic work | 1188 | Not in index |
| Design Arena: agents building Android appsAgentic work | 1192 | Not in index |
| Design Arena: agents building Godot gamesAgentic work | Not measured | Not in index |
| Design Arena: agents building gamesAgentic work | Not measured | 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 | 83.7% | Not in index |
| SWE-bench Verified (Vals AI)Coding | 76.4% | Not in index |
| Terminal-Bench 4 (Vals AI)Coding | Not measured | Not in index |
| Vibe Code Bench (Vals AI)Coding | 20.6% | 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 | 83.0% | Not in index |
| MATH 500 (Vals AI)Math | Not measured | Not in index |
| MGSM (Vals AI)Math | 95.2% | Not in index |
| SAGE (Vals AI)General | 52.1% | Not in index |
| LegalBench (Vals AI)Knowledge | 84.6% | Not in index |
| CaseLaw (Vals AI)Knowledge | 62.6% | Not in index |
| CorpFin (Vals AI)Knowledge | 65.1% | Not in index |
| TaxEval (Vals AI)Knowledge | 74.9% | Not in index |
| MortgageTax (Vals AI)Knowledge | 68.7% | Not in index |
| MedQA (Vals AI)Knowledge | 95.9% | Not in index |
| MedCode (Vals AI)Knowledge | 49.2% | Not in index |
| MedScribe (Vals AI)General | 85.3% | Not in index |
| Vals Multimodal IndexGeneral | Not measured | Not in index |
| AA Math IndexMath | 91.3 | Not in index |
| GPQA Diamond (Artificial Analysis run)Reasoning | 86.6% | Not in index |
| Humanity's Last Exam (Artificial Analysis run)Reasoning | 30.1% | Not in index |
| MMLU Pro (Artificial Analysis run)Knowledge | 89.5% | Not in index |
| LiveCodeBench (Artificial Analysis run)Coding | 87.1% | Not in index |
| SciCodeCoding | Not measured | Not in index |
| Terminal-Bench Hard (Artificial Analysis run)Coding | 47.0% | Not in index |
| IFBenchGeneral | 58.0% | Not in index |
| Long context reasoning (AA-LCR)General | 77.3% | Not in index |
| τ²-Bench TelecomAgentic work | 89.5% | Not in index |
| AIME 2025 (Artificial Analysis run)Math | 91.3% | Not in index |
| Terminal-BenchCoding | 63.1% | Not in index |
| DeepSWECoding | Not measured | Not in index |
| FrontierCodeCoding | Not measured | Not in index |
| FrontierSWECoding | Not measured | Not in index |
| GSO-BenchCoding | 26.5% | Not in index |
| WeirdMLCoding | 63.7% | Not in index |
| MirrorCodeCoding | Not measured | Not in index |
| APEX-AgentsAgentic work | Not measured | Not in index |
| METR time horizonsAgentic work | 75.0% | Not in index |
| Remote Labor IndexAgentic work | 3.8% | Not in index |
| GDPvalAgentic work | 45.5% | Not in index |
| OSWorld 2.0Agentic work | Not measured | Not in index |
| BALROGAgentic work | 43.5% | Not in index |
| DeepResearch BenchAgentic work | 54.8% | Not in index |
| PostTrainBenchAgentic work | Not measured | Not in index |
| GPQA Diamond (Epoch AI run)Reasoning | 86.0% | Not in index |
| ARC-AGIReasoning | 80.0% | Not in index |
| ARC-AGI-2Reasoning | 37.6% | Not in index |
| Humanity's Last ExamReasoning | 25.2% | Not in index |
| SimpleBenchReasoning | 62.0% | Not in index |
| Chess puzzlesReasoning | 14.0% | Not in index |
| Mystery game puzzlesReasoning | 22.0% | Not in index |
| EBR-benchReasoning | 14.3% | Not in index |
| OTIS Mock AIMEMath | 86.1% | Not in index |
| FrontierMath, tiers 1 to 3Math | 34.4% | Not in index |
| FrontierMath, tier 4Math | 4.9% | Not in index |
| ProofBenchMath | 36.0% | Not in index |
| MATH level 5Math | Not measured | Not in index |
| GSM8KMath | Not measured | Not in index |
| SimpleQA VerifiedKnowledge | 45.7% | Not in index |
| MMLUKnowledge | Not measured | Not in index |
| GeoBenchKnowledge | 75.0% | Not in index |
| DTBenchGeneral | 89.9% | Not in index |
| LMCAGeneral | 44.5% | Not in index |
| Fiction.LiveBenchGeneral | Not measured | Not in index |
| Creative writing (Lech Mazur)General | Not measured | Not in index |
| CL-benchGeneral | 21.1% | 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 | 82.0% | Not in index |
| TheAgentCompanyAgentic work | Not measured | Not in index |
| OSWorldAgentic work | 66.3% | Not in index |
| SpireClimbAgentic work | Not measured | Not in index |
| VPCTReasoning | 40.0% | 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 | Not measured | Not in index |
| ALE-BenchCoding | Not measured | Not in index |
| Vending-Bench 2Agentic work | $4,967 | Not in index |
| Epoch Capabilities IndexIntelligence | 150.2 | Not in index |
| LMArena TextGeneral | 1451 | Not in index |
| LMArena Text: codingCoding | 1499 | Not in index |
| LMArena Text: hard promptsReasoning | 1476 | Not in index |
| LMArena Text: mathMath | 1458 | Not in index |
| LMArena Text: instruction followingGeneral | 1472 | Not in index |
| LMArena Text: creative writingGeneral | 1443 | Not in index |
| LMArena VisionGeneral | Not measured | Not in index |
| LMArena Text: EnglishGeneral | 1461 | Not in index |
| LMArena Text: non-EnglishGeneral | 1438 | Not in index |
| LMArena Text: ChineseGeneral | 1470 | Not in index |
| LMArena Text: GermanGeneral | 1449 | Not in index |
| LMArena Text: JapaneseGeneral | 1412 | Not in index |
| LMArena Text: KoreanGeneral | 1424 | Not in index |
| LMArena Text: FrenchGeneral | 1471 | Not in index |
| LMArena Text: SpanishGeneral | 1453 | Not in index |
| LMArena Text: RussianGeneral | 1447 | Not in index |
| LMArena Text: PolishGeneral | 1439 | Not in index |
| LMArena Text: multi-turnGeneral | 1466 | Not in index |
| LMArena Text: longer queriesGeneral | 1479 | Not in index |
| LMArena Text: expertReasoning | 1487 | Not in index |
| LMArena Text: hard prompts in EnglishReasoning | 1482 | Not in index |
| LMArena Text: software and ITCoding | 1483 | Not in index |
| LMArena Text: mathematical workMath | 1469 | Not in index |
| LMArena Text: scienceKnowledge | 1454 | Not in index |
| LMArena Text: medicine and healthcareKnowledge | 1444 | Not in index |
| LMArena Text: legal and governmentKnowledge | 1459 | Not in index |
| LMArena Text: business and financeKnowledge | 1448 | Not in index |
| LMArena Text: writing and languageGeneral | 1451 | Not in index |
| LMArena Text: entertainment and mediaGeneral | 1434 | Not in index |
| LMArena WebDev: ReactCoding | 1478 | Not in index |
| LMArena WebDev: HTMLCoding | 1510 | Not in index |
| LMArena WebDev: from an imageCoding | Not measured | Not in index |
| LMArena Vision: EnglishGeneral | Not measured | Not in index |
| LMArena Vision: ChineseGeneral | Not measured | Not in index |
| LMArena Vision: reading textGeneral | Not measured | Not in index |
| LMArena Vision: diagramsReasoning | Not measured | Not in index |
| LMArena Vision: homeworkReasoning | Not measured | Not in index |
| LMArena Vision: humorGeneral | Not measured | Not in index |
| LMArena Vision: captioningGeneral | Not measured | Not in index |
| LMArena Vision: recognizing thingsGeneral | Not measured | Not in index |
| LMArena Vision: creative writingGeneral | Not measured | Not in index |
| LMArena SearchAgentic work | Not measured | Not in index |
| LMArena DocumentGeneral | 1462 | 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 Multilingual | 70.7% | $0.8336 per attempt | Nothing else |
| SWE-bench Verified (Vals AI) | 76.4% | $1.05 per test | Duration, as printed 5m 21s |
| Vibe Code Bench (Vals AI) | 20.6% | $32.87 per test | Duration, as printed 38m 03s |
| WeirdML | 63.7% | $0.7383 per run | Median lines of code 173 |
| ARC-AGI | 80.0% | $1.47 per task | Nothing else |
| ARC-AGI-2 | 37.6% | $2.40 per task | Nothing else |
| ProofBench | 36.0% | $1.267 per test | Time per proof 1h 03m |
| LMArena WebDev | 1494 Elo | Not published | Votes 11,029 · Interval (±) ±8.3 |
| GPQA Diamond | 85.9% | Not published | Latency, as printed 2m 19s |
| AIME | 95.4% | Not published | Latency, as printed 3m 32s |
| MMLU Pro | 87.3% | Not published | Latency, as printed 39 s |
| Design Arena: websites | 1247 Elo | Not published | Battles 21,788 |
| Design Arena: UI components | 1239 Elo | Not published | Battles 2,085 |
|---|---|---|---|
| Design Arena: game dev | 1229 Elo | Not published | Battles 5,034 |
| Design Arena: data viz | 1243 Elo | Not published | Battles 1,495 |
| Design Arena: 3D | 1214 Elo | Not published | Battles 6,015 |
| Design Arena: all code categories | 1242 Elo | Not published | Battles 35,207 |
| Design Arena: SVG | 1180 Elo | Not published | Battles 4,787 |
| Design Arena: ASCII art | 1190 Elo | Not published | Battles 429 |
| Design Arena: agents building web apps | 1159 Elo | Not published | Battles 2,697 |
| Design Arena: agents building full-stack apps | 1156 Elo | Not published | Battles 1,396 |
| Design Arena: agents building mobile apps | 1188 Elo | Not published | Battles 1,542 |
| Design Arena: agents building Android apps | 1192 Elo | Not published | Battles 661 |
| LiveCodeBench (Vals AI) | 83.7% | Not published | Latency, as printed 2m 44s |
| MMMU Pro (Vals AI) | 83.0% | Not published | Latency, as printed 1m 15s |
| MGSM (Vals AI) | 95.2% | Not published | Latency, as printed 12 s |
| SAGE (Vals AI) | 52.1% | Not published | Latency, as printed 1m 27s |
| LegalBench (Vals AI) | 84.6% | Not published | Latency, as printed 7.6 s |
| CaseLaw (Vals AI) | 62.6% | Not published | Latency, as printed 17 s |
| CorpFin (Vals AI) | 65.1% | Not published | Latency, as printed 18 s |
| TaxEval (Vals AI) | 74.9% | Not published | Latency, as printed 47 s |
| MortgageTax (Vals AI) | 68.7% | Not published | Latency, as printed 11 s |
| MedQA (Vals AI) | 95.9% | Not published | Latency, as printed 32 s |
| MedCode (Vals AI) | 49.2% | Not published | Latency, as printed 1m 01s |
| MedScribe (Vals AI) | 85.3% | Not published | Latency, as printed 1m 12s |
| LMArena Text | 1451 Elo | Not published | Votes 72,899 · Interval (±) ±3.1 |
| LMArena Text: coding | 1499 Elo | Not published | Votes 17,986 · Interval (±) ±5.3 |
| LMArena Text: hard prompts | 1476 Elo | Not published | Votes 43,250 · Interval (±) ±3.9 |
| LMArena Text: math | 1458 Elo | Not published | Votes 4,547 · Interval (±) ±9.0 |
| LMArena Text: instruction following | 1472 Elo | Not published | Votes 21,834 · Interval (±) ±5.0 |
| LMArena Text: creative writing | 1443 Elo | Not published | Votes 11,412 · Interval (±) ±6.3 |
| LMArena Text: English | 1461 Elo | Not published | Votes 31,213 · Interval (±) ±4.3 |
| LMArena Text: non-English | 1438 Elo | Not published | Votes 41,682 · Interval (±) ±3.9 |
| LMArena Text: Chinese | 1470 Elo | Not published | Votes 5,403 · Interval (±) ±8.5 |
| LMArena Text: German | 1449 Elo | Not published | Votes 1,134 · Interval (±) ±18.2 |
| LMArena Text: Japanese | 1412 Elo | Not published | Votes 640 · Interval (±) ±24.4 |
| LMArena Text: Korean | 1424 Elo | Not published | Votes 1,170 · Interval (±) ±18.2 |
| LMArena Text: French | 1471 Elo | Not published | Votes 2,026 · Interval (±) ±14.5 |
| LMArena Text: Spanish | 1453 Elo | Not published | Votes 2,162 · Interval (±) ±13.5 |
| LMArena Text: Russian | 1447 Elo | Not published | Votes 9,053 · Interval (±) ±6.7 |
| LMArena Text: Polish | 1439 Elo | Not published | Votes 1,891 · Interval (±) ±13.6 |
| LMArena Text: multi-turn | 1466 Elo | Not published | Votes 12,968 · Interval (±) ±6.0 |
| LMArena Text: longer queries | 1479 Elo | Not published | Votes 24,254 · Interval (±) ±4.9 |
| LMArena Text: expert | 1487 Elo | Not published | Votes 5,688 · Interval (±) ±8.3 |
| LMArena Text: hard prompts in English | 1482 Elo | Not published | Votes 18,759 · Interval (±) ±5.2 |
| LMArena Text: software and IT | 1483 Elo | Not published | Votes 26,901 · Interval (±) ±4.6 |
| LMArena Text: mathematical work | 1469 Elo | Not published | Votes 3,778 · Interval (±) ±9.9 |
| LMArena Text: science | 1454 Elo | Not published | Votes 11,580 · Interval (±) ±6.1 |
| LMArena Text: medicine and healthcare | 1444 Elo | Not published | Votes 4,920 · Interval (±) ±8.9 |
| LMArena Text: legal and government | 1459 Elo | Not published | Votes 5,431 · Interval (±) ±8.5 |
| LMArena Text: business and finance | 1448 Elo | Not published | Votes 14,098 · Interval (±) ±5.7 |
| LMArena Text: writing and language | 1451 Elo | Not published | Votes 16,912 · Interval (±) ±5.4 |
| LMArena Text: entertainment and media | 1434 Elo | Not published | Votes 14,080 · Interval (±) ±5.8 |
| LMArena WebDev: React | 1478 Elo | Not published | Votes 4,740 · Interval (±) ±10.6 |
| LMArena WebDev: HTML | 1510 Elo | Not published | Votes 6,278 · Interval (±) ±12.6 |
| LMArena Document | 1462 Elo | Not published | Votes 7,981 · Interval (±) ±10.4 |