Anthropic Claude Sonnet 4 was last priced at $3.00 per million input tokens and $15.00 per million output tokens, as of October 22, 2026. None of the 6 coding benchmarks behind the index has measured it, so it has no coding index, but 81 benchmarks outside the index have a result below.
Claude Sonnet 4 is retired, so it sits outside the current price order and the rankings.
No longer sold through the API. Retired on June 15, 2026; last list price shown.
OpenRouter publishes no description for this model.
anthropic/claude-sonnet-4 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 3 of 7 categories. A retired model is on no leaderboard, so it has no place.
No coding benchmark has measured this model, so there is no index. We do not estimate one from its price, its maker or its siblings. How it is weighted
Not measured on SWE-bench Lite, SWE-bench (full test set), SWE-bench Multilingual, AA Coding Index, 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, Terminal-Bench Hard (Artificial Analysis run), Terminal-Bench, DeepSWE, FrontierSWE, MirrorCode, ALE-Bench, LMArena WebDev: React, LMArena WebDev: HTML, LMArena WebDev: from an image, SWE-Bench Pro V2, SWE Atlas: Codebase QnA, SWE Atlas: Refactoring, SWE Atlas: Test Writing
Not measured on AA Intelligence Index
Not measured on AA Agentic Index, Design Arena: agents building web apps, Design Arena: agents building full-stack apps, Design Arena: agents building mobile apps, Design Arena: agents building Android apps, 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), τ²-Bench Telecom, APEX-Agents, Remote Labor Index, GDPval, OSWorld 2.0, BALROG, PostTrainBench, SpireClimb, Vending-Bench 2, LMArena Search, Berkeley Function Calling Leaderboard (BFCL), MCP Atlas
Not measured on LiveBench reasoning, MysteryMechanism (Vals AI), GPQA Diamond (Artificial Analysis run), Humanity's Last Exam (Artificial Analysis run), Humanity's Last Exam, Chess puzzles, Mystery game puzzles, EBR-bench, BIG-Bench Hard, Kagi LLM Benchmark, Humanity's Last Exam (Scale run)
Not measured on AA Math Index, AIME 2025 (Artificial Analysis run), FrontierMath, tiers 1 to 3, FrontierMath, tier 4, ProofBench, GSM8K, MathArena
Not measured on CaseLaw (Vals AI), MMLU Pro (Artificial Analysis run), SimpleQA Verified, MMLU, AI2 Reasoning Challenge, PRBench Finance, PRBench Legal
Not measured on Design Arena: ASCII art, LiveBench design
Not measured on Vals Index, LiveBench data analysis, Public Benefits Bench (Vals AI), Vals Multimodal Index, IFBench, Long context reasoning (AA-LCR), CL-bench, Surface Evolver Bench, Furniture assembly, ExploitBench, HellaSwag, WinoGrande, PIQA, CL-bench Life, LMArena Vision: Chinese, LMArena Vision: humor, LMArena Vision: captioning, LMArena Vision: recognizing things, LMArena Vision: creative writing, LMArena Document, MultiChallenge, EQ-Bench 4
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 | 61.3%(32k thinking) | Not in index |
| SWE-bench VerifiedCoding | 76.8% | Not in index |
| SWE-bench LiteCoding | Not measured | Not in index |
| SWE-bench (full test set)Coding | Not measured | Not in index |
| SWE-bench MultimodalCoding | 34.4% | Not in index |
| SWE-bench MultilingualCoding | Not measured | Not in index |
| LiveBench codingCoding | Not measured | 15% |
| LMArena WebDevCoding | Not measured | 10% |
| Vals IndexGeneral | Not measured | Not in index |
| GPQA DiamondReasoning | 75.0%(Thinking) | Not in index |
| AIMEMath | 76.3%(Thinking) | Not in index |
| MMLU ProKnowledge | 83.9%(Thinking) | Not in index |
| AA Intelligence IndexIntelligence | Not measured | Not in index |
| AA Coding IndexCoding | Not measured | Not in index |
| AA Agentic IndexAgentic work | Not measured | Not in index |
| Design Arena: websitesWeb design | 1146 | Not in index |
| Design Arena: UI componentsWeb design | 1126 | Not in index |
| Design Arena: game devWeb design | 1138(Thinking) | Not in index |
| Design Arena: data vizWeb design | 1158(Thinking) | Not in index |
| Design Arena: 3DWeb design | 1139 | Not in index |
| Design Arena: all code categoriesWeb design | 1141 | Not in index |
| Design Arena: SVGWeb design | 1078(Thinking) | Not in index |
| Design Arena: ASCII artWeb design | Not measured | Not in index |
| Design Arena: agents building web appsAgentic work | Not measured | Not in index |
| Design Arena: agents building full-stack appsAgentic work | Not measured | Not in index |
| Design Arena: agents building mobile appsAgentic work | Not measured | Not in index |
| Design Arena: agents building Android appsAgentic work | Not measured | 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 | 62.4%(Thinking) | Not in index |
| SWE-bench Verified (Vals AI)Coding | Not measured | 15% |
| Terminal-Bench 4 (Vals AI)Coding | Not measured | 25% |
| Vibe Code Bench (Vals AI)Coding | Not measured | 20% |
| 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 | 74.9%(Thinking) | Not in index |
| MATH 500 (Vals AI)Math | 93.8%(Thinking) | Not in index |
| MGSM (Vals AI)Math | 93.0%(No thinking) | Not in index |
| SAGE (Vals AI)General | 35.0%(No thinking) | Not in index |
| LegalBench (Vals AI)Knowledge | 83.0%(No thinking) | Not in index |
| CaseLaw (Vals AI)Knowledge | Not measured | Not in index |
| CorpFin (Vals AI)Knowledge | 61.2%(Thinking) | Not in index |
| TaxEval (Vals AI)Knowledge | 72.0%(Thinking) | Not in index |
| MortgageTax (Vals AI)Knowledge | 62.5%(No thinking) | Not in index |
| MedQA (Vals AI)Knowledge | 92.7%(Thinking) | Not in index |
| MedCode (Vals AI)Knowledge | 35.0%(Thinking) | Not in index |
| MedScribe (Vals AI)General | 72.4%(No thinking) | 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 | Not measured | Not in index |
| Humanity's Last Exam (Artificial Analysis run)Reasoning | Not measured | 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 | Not measured | Not in index |
| IFBenchGeneral | Not measured | Not in index |
| Long context reasoning (AA-LCR)General | Not measured | Not in index |
| τ²-Bench TelecomAgentic work | Not measured | Not in index |
| AIME 2025 (Artificial Analysis run)Math | Not measured | Not in index |
| Terminal-BenchCoding | Not measured | Not in index |
| DeepSWECoding | Not measured | Not in index |
| FrontierCodeCoding | Not measured | 15% |
| FrontierSWECoding | Not measured | Not in index |
| GSO-BenchCoding | 4.9% | Not in index |
| WeirdMLCoding | 46.1%(16k thinking) | Not in index |
| MirrorCodeCoding | Not measured | Not in index |
| APEX-AgentsAgentic work | Not measured | Not in index |
| METR time horizonsAgentic work | 62.0%(16k thinking) | Not in index |
| Remote Labor IndexAgentic work | Not measured | 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 | 46.6%(2k thinking) | Not in index |
| PostTrainBenchAgentic work | Not measured | Not in index |
| GPQA Diamond (Epoch AI run)Reasoning | 79.2%(59k thinking) | Not in index |
| ARC-AGIReasoning | 40.0%(16k thinking) | Not in index |
| ARC-AGI-2Reasoning | 5.9%(16k thinking) | Not in index |
| Humanity's Last ExamReasoning | Not measured | Not in index |
| SimpleBenchReasoning | 45.5%(12k thinking) | Not in index |
| Chess puzzlesReasoning | Not measured | Not in index |
| Mystery game puzzlesReasoning | Not measured | Not in index |
| EBR-benchReasoning | Not measured | Not in index |
| OTIS Mock AIMEMath | 71.1%(32k thinking) | Not in index |
| FrontierMath, tiers 1 to 3Math | Not measured | Not in index |
| FrontierMath, tier 4Math | Not measured | Not in index |
| ProofBenchMath | Not measured | Not in index |
| MATH level 5Math | 84.4% | Not in index |
| GSM8KMath | Not measured | Not in index |
| SimpleQA VerifiedKnowledge | Not measured | Not in index |
| MMLUKnowledge | Not measured | Not in index |
| GeoBenchKnowledge | 37.0% | Not in index |
| DTBenchGeneral | 77.1% | Not in index |
| LMCAGeneral | 29.0% | Not in index |
| Fiction.LiveBenchGeneral | 46.9% | Not in index |
| Creative writing (Lech Mazur)General | 81.4%(16k thinking) | Not in index |
| CL-benchGeneral | Not measured | Not in index |
| Surface Evolver BenchGeneral | Not measured | Not in index |
| Furniture assemblyGeneral | Not measured | Not in index |
| ExploitBenchGeneral | Not measured | Not in index |
| CybenchCoding | 35.0% | Not in index |
| TheAgentCompanyAgentic work | 33.1% | Not in index |
| OSWorldAgentic work | 43.9% | Not in index |
| SpireClimbAgentic work | Not measured | Not in index |
| VPCTReasoning | 34.0%(32k thinking) | 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 | Not measured | Not in index |
| Epoch Capabilities IndexIntelligence | 141.6 | Not in index |
| LMArena TextGeneral | 1351(32k thinking) | Not in index |
| LMArena Text: codingCoding | 1414(32k thinking) | Not in index |
| LMArena Text: hard promptsReasoning | 1373(32k thinking) | Not in index |
| LMArena Text: mathMath | 1375(32k thinking) | Not in index |
| LMArena Text: instruction followingGeneral | 1376(32k thinking) | Not in index |
| LMArena Text: creative writingGeneral | 1345(32k thinking) | Not in index |
| LMArena VisionGeneral | 1191(32k thinking) | Not in index |
| LMArena Text: EnglishGeneral | 1364(32k thinking) | Not in index |
| LMArena Text: non-EnglishGeneral | 1333(32k thinking) | Not in index |
| LMArena Text: ChineseGeneral | 1350(32k thinking) | Not in index |
| LMArena Text: GermanGeneral | 1331 | Not in index |
| LMArena Text: JapaneseGeneral | 1302 | Not in index |
| LMArena Text: KoreanGeneral | 1290 | Not in index |
| LMArena Text: FrenchGeneral | 1363 | Not in index |
| LMArena Text: SpanishGeneral | 1357(32k thinking) | Not in index |
| LMArena Text: RussianGeneral | 1355(32k thinking) | Not in index |
| LMArena Text: PolishGeneral | 1324(32k thinking) | Not in index |
| LMArena Text: multi-turnGeneral | 1377(32k thinking) | Not in index |
| LMArena Text: longer queriesGeneral | 1398(32k thinking) | Not in index |
| LMArena Text: expertReasoning | 1372(32k thinking) | Not in index |
| LMArena Text: hard prompts in EnglishReasoning | 1385(32k thinking) | Not in index |
| LMArena Text: software and ITCoding | 1384(32k thinking) | Not in index |
| LMArena Text: mathematical workMath | 1379(32k thinking) | Not in index |
| LMArena Text: scienceKnowledge | 1346(32k thinking) | Not in index |
| LMArena Text: medicine and healthcareKnowledge | 1330 | Not in index |
| LMArena Text: legal and governmentKnowledge | 1342 | Not in index |
| LMArena Text: business and financeKnowledge | 1318 | Not in index |
| LMArena Text: writing and languageGeneral | 1357(32k thinking) | Not in index |
| LMArena Text: entertainment and mediaGeneral | 1332(32k thinking) | Not in index |
| LMArena WebDev: ReactCoding | Not measured | Not in index |
| LMArena WebDev: HTMLCoding | Not measured | Not in index |
| LMArena WebDev: from an imageCoding | Not measured | Not in index |
| LMArena Vision: EnglishGeneral | 1186(32k thinking) | Not in index |
| LMArena Vision: ChineseGeneral | Not measured | Not in index |
| LMArena Vision: reading textGeneral | 1197(32k thinking) | Not in index |
| LMArena Vision: diagramsReasoning | 1200(32k thinking) | Not in index |
| LMArena Vision: homeworkReasoning | 1215 | 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 | Not measured | Not in index |
| LMArena Text to ImageImage generation | Not measured | Not in index |
| LMArena Image EditImage generation | Not measured | Not in index |
| Berkeley Function Calling Leaderboard (BFCL)Agentic work | Not measured | Not in index |
| Kagi LLM BenchmarkReasoning | Not measured | Not in index |
| BrowseComp-PlusAgentic work | 37.4%(Sonnet 4 with Qwen3-Embed-8B) | Not in index |
| SciCodeCoding | 7.7% | Not in index |
| FACTS Benchmark SuiteKnowledge | 35.0% | Not in index |
| MathArenaMath | Not measured | Not in index |
| MultiChallengeGeneral | Not measured | Not in index |
| MCP AtlasAgentic work | Not measured | Not in index |
| Humanity's Last Exam (Scale run)Reasoning | Not measured | Not in index |
| PRBench FinanceKnowledge | Not measured | Not in index |
| PRBench LegalKnowledge | Not measured | Not in index |
| SWE-Bench Pro V2Coding | Not measured | Not in index |
| SWE Atlas: Codebase QnACoding | Not measured | Not in index |
| SWE Atlas: RefactoringCoding | Not measured | Not in index |
| SWE Atlas: Test WritingCoding | Not measured | Not in index |
| EQ-Bench 4General | Not measured | Not in index |
Some boards test this model at more than one reasoning effort. Rankings use its best run; every run the source published is listed here.
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.
SWE-bench Verified lists a pass rate for this model but no cost per attempt, on Vals AI and on swebench.com alike. We leave the number out rather than estimate it.
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 |
|---|---|---|---|
| Aider polyglot | 61.3%(32k thinking) | $26.58 of the run | Solved on the first try 25.8% · Edits well formed 97.3% · Time per exercise 1m 20s · Input tokens, whole run 2.9M · Output tokens, whole run 1.3M |
| WeirdML | 46.1%(16k thinking) | $0.336 per run | Median lines of code 198 |
| ARC-AGI | 40.0%(16k thinking) | $0.3658 per task | Nothing else |
| ARC-AGI-2 | 5.9%(16k thinking) | $0.4857 per task | Nothing else |
| TheAgentCompany | 33.1% | $1.63 average cost per task | Nothing else |
| GPQA Diamond | 75.0%(Thinking) | Not published | Latency, as printed 1m 58s |
| AIME | 76.3%(Thinking) | Not published | Latency, as printed 4m 32s |
| MMLU Pro | 83.9%(Thinking) | Not published | Latency, as printed 47 s |
| Design Arena: websites | 1146 Elo | Not published | Battles 13,465 |
| Design Arena: UI components | 1126 Elo | Not published | Battles 598 |
| Design Arena: game dev | 1138 Elo(Thinking) | Not published | Battles 1,585 |
| Design Arena: data viz | 1158 Elo(Thinking) | Not published | Battles 170 |
| Design Arena: 3D | 1139 Elo | Not published | Battles 1,574 |
|---|---|---|---|
| Design Arena: all code categories | 1141 Elo | Not published | Battles 17,542 |
| Design Arena: SVG | 1078 Elo(Thinking) | Not published | Battles 1,788 |
| LiveCodeBench (Vals AI) | 62.4%(Thinking) | Not published | Latency, as printed 43 s |
| MMMU Pro (Vals AI) | 74.9%(Thinking) | Not published | Latency, as printed 49 s |
| MATH 500 (Vals AI) | 93.8%(Thinking) | Not published | Latency, as printed 1m 03s |
| MGSM (Vals AI) | 93.0%(No thinking) | Not published | Latency, as printed 6.0 s |
| SAGE (Vals AI) | 35.0%(No thinking) | Not published | Latency, as printed 17 s |
| LegalBench (Vals AI) | 83.0%(No thinking) | Not published | Latency, as printed 4.8 s |
| CorpFin (Vals AI) | 61.2%(Thinking) | Not published | Latency, as printed 2m 49s |
| TaxEval (Vals AI) | 72.0%(Thinking) | Not published | Latency, as printed 32 s |
| MortgageTax (Vals AI) | 62.5%(No thinking) | Not published | Latency, as printed 8.4 s |
| MedQA (Vals AI) | 92.7%(Thinking) | Not published | Latency, as printed 27 s |
| MedCode (Vals AI) | 35.0%(Thinking) | Not published | Latency, as printed 40 s |
| MedScribe (Vals AI) | 72.4%(No thinking) | Not published | Latency, as printed 26 s |
| LMArena Text | 1351 Elo(32k thinking) | Not published | Votes 34,138 · Interval (±) ±4.5 |
| LMArena Text: coding | 1414 Elo(32k thinking) | Not published | Votes 6,349 · Interval (±) ±7.9 |
| LMArena Text: hard prompts | 1373 Elo(32k thinking) | Not published | Votes 15,423 · Interval (±) ±5.7 |
| LMArena Text: math | 1375 Elo(32k thinking) | Not published | Votes 2,015 · Interval (±) ±12.9 |
| LMArena Text: instruction following | 1376 Elo(32k thinking) | Not published | Votes 8,527 · Interval (±) ±7.0 |
| LMArena Text: creative writing | 1345 Elo(32k thinking) | Not published | Votes 4,251 · Interval (±) ±9.5 |
| LMArena Vision | 1191 Elo(32k thinking) | Not published | Votes 1,144 · Interval (±) ±16.9 |
| LMArena Text: English | 1364 Elo(32k thinking) | Not published | Votes 14,849 · Interval (±) ±5.8 |
| LMArena Text: non-English | 1333 Elo(32k thinking) | Not published | Votes 19,284 · Interval (±) ±5.4 |
| LMArena Text: Chinese | 1350 Elo(32k thinking) | Not published | Votes 2,376 · Interval (±) ±12.3 |
| LMArena Text: German | 1331 Elo | Not published | Votes 1,082 · Interval (±) ±18.7 |
| LMArena Text: Japanese | 1302 Elo | Not published | Votes 970 · Interval (±) ±19.9 |
| LMArena Text: Korean | 1290 Elo | Not published | Votes 927 · Interval (±) ±20.6 |
| LMArena Text: French | 1363 Elo | Not published | Votes 570 · Interval (±) ±25.2 |
| LMArena Text: Spanish | 1357 Elo(32k thinking) | Not published | Votes 835 · Interval (±) ±21.3 |
| LMArena Text: Russian | 1355 Elo(32k thinking) | Not published | Votes 2,415 · Interval (±) ±11.8 |
| LMArena Text: Polish | 1324 Elo(32k thinking) | Not published | Votes 3,272 · Interval (±) ±11.4 |
| LMArena Text: multi-turn | 1377 Elo(32k thinking) | Not published | Votes 5,636 · Interval (±) ±8.4 |
| LMArena Text: longer queries | 1398 Elo(32k thinking) | Not published | Votes 6,727 · Interval (±) ±7.7 |
| LMArena Text: expert | 1372 Elo(32k thinking) | Not published | Votes 1,702 · Interval (±) ±14.5 |
| LMArena Text: hard prompts in English | 1385 Elo(32k thinking) | Not published | Votes 6,984 · Interval (±) ±7.6 |
| LMArena Text: software and IT | 1384 Elo(32k thinking) | Not published | Votes 11,262 · Interval (±) ±6.3 |
| LMArena Text: mathematical work | 1379 Elo(32k thinking) | Not published | Votes 1,915 · Interval (±) ±13.3 |
| LMArena Text: science | 1346 Elo(32k thinking) | Not published | Votes 5,614 · Interval (±) ±8.3 |
| LMArena Text: medicine and healthcare | 1330 Elo | Not published | Votes 2,365 · Interval (±) ±13.0 |
| LMArena Text: legal and government | 1342 Elo | Not published | Votes 2,621 · Interval (±) ±12.1 |
| LMArena Text: business and finance | 1318 Elo | Not published | Votes 6,538 · Interval (±) ±8.0 |
| LMArena Text: writing and language | 1357 Elo(32k thinking) | Not published | Votes 7,377 · Interval (±) ±7.4 |
| LMArena Text: entertainment and media | 1332 Elo(32k thinking) | Not published | Votes 6,044 · Interval (±) ±8.1 |
| LMArena Vision: English | 1186 Elo(32k thinking) | Not published | Votes 526 · Interval (±) ±25.1 |
| LMArena Vision: reading text | 1197 Elo(32k thinking) | Not published | Votes 725 · Interval (±) ±21.5 |
| LMArena Vision: diagrams | 1200 Elo(32k thinking) | Not published | Votes 228 · Interval (±) ±36.7 |
| LMArena Vision: homework | 1215 Elo | Not published | Votes 230 · Interval (±) ±35.9 |
No comparison page of its own yet: one needs a coding index on both sides, and Claude Sonnet 4 has none. Compare Claude Sonnet 4 with any model