As of October 20, 2026, Anthropic Claude Opus 5 ranks #7 of 213 models overall with 50.8 on the Artificial Analysis Intelligence Index. Its strongest category is knowledge, where it ranks #2 of 147. Anthropic Claude Opus 5 costs $5.00 per million input tokens and $25.00 per million output tokens. It was released on July 24, 2026.
Its output price ranks 327 of 349 priced models, counting from the cheapest.
Claude Opus 5 is Anthropic’s flagship model for demanding reasoning, coding, and long-horizon agentic work. It is particularly strong at end-to-end software tasks, code review and bug finding, visual analysis...
anthropic/claude-opus-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 6 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, SWE-bench Multilingual, SWE-bench Multimodal (Vals AI), LiveCodeBench (Artificial Analysis run), Terminal-Bench Hard (Artificial Analysis run), Terminal-Bench, GSO-Bench, MirrorCode, Cybench
Not measured on Design Arena: HTML slides, Design Arena: spreadsheets, Harvey's Legal Agent Benchmark (Vals AI), Robo-bench (Vals AI), τ²-Bench Telecom, METR time horizons, Remote Labor Index, GDPval, DeepResearch Bench, TheAgentCompany, OSWorld, SpireClimb
Not measured on Humanity's Last Exam, VPCT, BIG-Bench Hard
Not measured on AIME, MATH 500 (Vals AI), MGSM (Vals AI), AA Math Index, AIME 2025 (Artificial Analysis run), MATH level 5, GSM8K
Not measured on CaseLaw (Vals AI), MedQA (Vals AI), MMLU Pro (Artificial Analysis run), MMLU, GeoBench, AI2 Reasoning Challenge
Not measured on Vals Index, IFBench, Fiction.LiveBench, Creative writing (Lech Mazur), CL-bench, Surface Evolver Bench, ExploitBench, HellaSwag, WinoGrande, PIQA, CL-bench Life, LMArena Vision: captioning, LMArena Vision: recognizing things
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 | Not measured | 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 | Not measured | Not in index |
| LiveBench codingCoding | 90.8% | 20% |
| LMArena WebDevCoding | 1689 | 15% |
| Vals IndexGeneral | Not measured | Not in index |
| GPQA DiamondReasoning | 93.4% | Not in index |
| AIMEMath | Not measured | Not in index |
| MMLU ProKnowledge | 91.6% | Not in index |
| AA Intelligence IndexIntelligence | 50.8 | Not in index |
| AA Coding IndexCoding | 78.0 | Not in index |
| AA Agentic IndexAgentic work | 56.5 | Not in index |
| Design Arena: websitesWeb design | 1310 | Not in index |
| Design Arena: UI componentsWeb design | 1348 | Not in index |
| Design Arena: game devWeb design | 1337 | Not in index |
| Design Arena: data vizWeb design | 1329 | Not in index |
| Design Arena: 3DWeb design | 1335 | Not in index |
| Design Arena: all code categoriesWeb design | 1324 | Not in index |
| Design Arena: SVGWeb design | 1310 | Not in index |
| Design Arena: ASCII artWeb design | 1352 | Not in index |
| Design Arena: agents building web appsAgentic work | 1266 | Not in index |
| Design Arena: agents building full-stack appsAgentic work | 1306 | Not in index |
| Design Arena: agents building mobile appsAgentic work | 1348 | Not in index |
| Design Arena: agents building Android appsAgentic work | 1267 | Not in index |
| Design Arena: agents building Godot gamesAgentic work | 1279 | Not in index |
| Design Arena: agents building gamesAgentic work | 1262 | Not in index |
| Design Arena: HTML slidesAgentic work | Not measured | Not in index |
| Design Arena: PowerPoint slidesAgentic work | 1266 | 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 | 91.2% | Not in index |
| LiveBench data analysisGeneral | 74.6% | Not in index |
| LiveBench researchAgentic work | 88.9% | Not in index |
| LiveBench browserAgentic work | 84.0% | Not in index |
| LiveBench long agenticAgentic work | 62.1% | Not in index |
| LiveBench designWeb design | 83.0% | Not in index |
| LiveCodeBench (Vals AI)Coding | 89.0% | Not in index |
| SWE-bench Verified (Vals AI)Coding | 97.0% | Not in index |
| Terminal-Bench 4 (Vals AI)Coding | 53.5% | Not in index |
| Vibe Code Bench (Vals AI)Coding | 88.4% | Not in index |
| Code migration (Vals AI)Coding | 57.5% | Not in index |
| ProgramBench (Vals AI)Coding | 3.0% | Not in index |
| SREBench (Vals AI)Agentic work | 12.2% | Not in index |
| IOI (Vals AI)Coding | 84.3% | Not in index |
| Terminal-Bench 2.1 (Vals AI)Coding | 84.6% | Not in index |
| SWE-bench Multimodal (Vals AI)Coding | Not measured | Not in index |
| Vibe Code Bench 1-100 (Vals AI)Coding | 28.5% | Not in index |
| SkillsBench (Vals AI)Coding | 60.4% | Not in index |
| CyberBench (Vals AI)Coding | 65.4% | Not in index |
| Finance Agent (Vals AI)Agentic work | 58.6% | Not in index |
| Tax Agent Bench (Vals AI)Agentic work | 45.5% | Not in index |
| Legal Research Bench (Vals AI)Agentic work | 55.3% | Not in index |
| Harvey's Legal Agent Benchmark (Vals AI)Agentic work | Not measured | Not in index |
| Excel Modeling Benchmark (Vals AI)Agentic work | 73.6% | Not in index |
| BioMysteryBench (Vals AI)Agentic work | 79.3% | Not in index |
| Terminal-Bench-Science (Vals AI)Agentic work | 27.1% | Not in index |
| Vals Science IndexAgentic work | 47.9% | Not in index |
| Time Horizon Index (Vals AI)Agentic work | 18.8% | Not in index |
| CUA-bench (Vals AI)Agentic work | 9.0% | Not in index |
| Robo-bench (Vals AI)Agentic work | Not measured | Not in index |
| Public Benefits Bench (Vals AI)General | 76.9% | Not in index |
| MysteryMechanism (Vals AI)Reasoning | 37.4% | Not in index |
| MMMU Pro (Vals AI)Reasoning | 89.9% | 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 | 49.4% | Not in index |
| LegalBench (Vals AI)Knowledge | 87.0% | Not in index |
| CaseLaw (Vals AI)Knowledge | Not measured | Not in index |
| CorpFin (Vals AI)Knowledge | 73.2% | Not in index |
| TaxEval (Vals AI)Knowledge | 75.1% | Not in index |
| MortgageTax (Vals AI)Knowledge | 72.1% | Not in index |
| MedQA (Vals AI)Knowledge | Not measured | Not in index |
| MedCode (Vals AI)Knowledge | 63.6% | Not in index |
| MedScribe (Vals AI)General | 91.0% | Not in index |
| Vals Multimodal IndexGeneral | 73.9% | Not in index |
| AA Math IndexMath | Not measured | Not in index |
| GPQA Diamond (Artificial Analysis run)Reasoning | 93.7% | Not in index |
| Humanity's Last Exam (Artificial Analysis run)Reasoning | 54.9% | 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 | 56.4% | 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 | 82.0% | 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 | 73.6% | Not in index |
| FrontierCodeCoding | 53.4% | Not in index |
| FrontierSWECoding | 52.0% | Not in index |
| GSO-BenchCoding | Not measured | Not in index |
| WeirdMLCoding | 91.8% | Not in index |
| MirrorCodeCoding | Not measured | Not in index |
| APEX-AgentsAgentic work | 65.8% | Not in index |
| METR time horizonsAgentic work | Not measured | Not in index |
| Remote Labor IndexAgentic work | Not measured | Not in index |
| GDPvalAgentic work | Not measured | Not in index |
| OSWorld 2.0Agentic work | 31.4% | Not in index |
| BALROGAgentic work | 63.4% | Not in index |
| DeepResearch BenchAgentic work | Not measured | Not in index |
| PostTrainBenchAgentic work | 35.0% | Not in index |
| GPQA Diamond (Epoch AI run)Reasoning | 93.9% | Not in index |
| ARC-AGIReasoning | 97.5% | Not in index |
| ARC-AGI-2Reasoning | 90.4% | Not in index |
| Humanity's Last ExamReasoning | Not measured | Not in index |
| SimpleBenchReasoning | 80.6% | Not in index |
| Chess puzzlesReasoning | 43.0% | Not in index |
| Mystery game puzzlesReasoning | 59.0% | Not in index |
| EBR-benchReasoning | 45.7% | Not in index |
| OTIS Mock AIMEMath | 98.9% | Not in index |
| FrontierMath, tiers 1 to 3Math | 85.6% | Not in index |
| FrontierMath, tier 4Math | 73.2% | Not in index |
| ProofBenchMath | 99.0% | Not in index |
| MATH level 5Math | Not measured | Not in index |
| GSM8KMath | Not measured | Not in index |
| SimpleQA VerifiedKnowledge | 59.9% | Not in index |
| MMLUKnowledge | Not measured | Not in index |
| GeoBenchKnowledge | Not measured | Not in index |
| DTBenchGeneral | 97.9% | Not in index |
| LMCAGeneral | 64.5% | Not in index |
| Fiction.LiveBenchGeneral | Not measured | Not in index |
| Creative writing (Lech Mazur)General | Not measured | Not in index |
| CL-benchGeneral | Not measured | Not in index |
| Surface Evolver BenchGeneral | Not measured | Not in index |
| Furniture assemblyGeneral | 60.8% | Not in index |
| ExploitBenchGeneral | Not measured | Not in index |
| CybenchCoding | Not measured | 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 | Not measured | Not in index |
| ALE-BenchCoding | 2164.6 | Not in index |
| Vending-Bench 2Agentic work | $11,182 | Not in index |
| Epoch Capabilities IndexIntelligence | 162.6 | Not in index |
| LMArena TextGeneral | 1508 | Not in index |
| LMArena Text: codingCoding | 1533 | Not in index |
| LMArena Text: hard promptsReasoning | 1526 | Not in index |
| LMArena Text: mathMath | 1532 | Not in index |
| LMArena Text: instruction followingGeneral | 1518 | Not in index |
| LMArena Text: creative writingGeneral | 1492 | Not in index |
| LMArena VisionGeneral | 1320 | Not in index |
| LMArena Text: EnglishGeneral | 1507 | Not in index |
| LMArena Text: non-EnglishGeneral | 1500 | Not in index |
| LMArena Text: ChineseGeneral | 1573 | Not in index |
| LMArena Text: GermanGeneral | 1526 | Not in index |
| LMArena Text: JapaneseGeneral | 1515 | Not in index |
| LMArena Text: KoreanGeneral | 1521 | Not in index |
| LMArena Text: FrenchGeneral | 1520 | Not in index |
| LMArena Text: SpanishGeneral | 1519 | Not in index |
| LMArena Text: RussianGeneral | 1507 | Not in index |
| LMArena Text: PolishGeneral | 1520 | Not in index |
| LMArena Text: multi-turnGeneral | 1499 | Not in index |
| LMArena Text: longer queriesGeneral | 1516 | Not in index |
| LMArena Text: expertReasoning | 1555 | Not in index |
| LMArena Text: hard prompts in EnglishReasoning | 1523 | Not in index |
| LMArena Text: software and ITCoding | 1527 | Not in index |
| LMArena Text: mathematical workMath | 1544 | Not in index |
| LMArena Text: scienceKnowledge | 1531 | Not in index |
| LMArena Text: medicine and healthcareKnowledge | 1526 | Not in index |
| LMArena Text: legal and governmentKnowledge | 1529 | Not in index |
| LMArena Text: business and financeKnowledge | 1501 | Not in index |
| LMArena Text: writing and languageGeneral | 1498 | Not in index |
| LMArena Text: entertainment and mediaGeneral | 1480 | Not in index |
| LMArena WebDev: ReactCoding | 1711 | Not in index |
| LMArena WebDev: HTMLCoding | 1680 | Not in index |
| LMArena WebDev: from an imageCoding | 1662 | Not in index |
| LMArena Vision: EnglishGeneral | 1315 | Not in index |
| LMArena Vision: ChineseGeneral | 1400 | Not in index |
| LMArena Vision: reading textGeneral | 1329 | Not in index |
| LMArena Vision: diagramsReasoning | 1348 | Not in index |
| LMArena Vision: homeworkReasoning | 1338 | Not in index |
| LMArena Vision: humorGeneral | 1293 | Not in index |
| LMArena Vision: captioningGeneral | Not measured | Not in index |
| LMArena Vision: recognizing thingsGeneral | Not measured | Not in index |
| LMArena Vision: creative writingGeneral | 1313 | Not in index |
| LMArena SearchAgentic work | 1242 | Not in index |
| LMArena DocumentGeneral | 1516 | 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 |
|---|---|---|---|
| LiveBench coding | 90.8% | $3.9218 per task | Output tokens per task 35,875 |
| LiveBench reasoning | 91.2% | $0.1684 per task | Output tokens per task 6,406 |
| LiveBench data analysis | 74.6% | $0.7455 per task | Output tokens per task 29,014 |
| LiveBench research | 88.9% | $16.9704 per task | Output tokens per task 76,872 |
| LiveBench browser | 84.0% | $2.9653 per task | Output tokens per task 17,216 |
| LiveBench long agentic | 62.1% | $48.7532 per task | Output tokens per task 384,099 |
| LiveBench design | 83.0% | $5.4526 per task | Output tokens per task 58,259 |
| SWE-bench Verified (Vals AI) | 97.0% | $1.29 per test | Duration, as printed 9m 37s |
| Terminal-Bench 4 (Vals AI) | 53.5% | $18.60 per test | Duration, as printed 1h 07m |
| Vibe Code Bench (Vals AI) | 88.4% | $33.88 per test | Duration, as printed 1h 28m |
| Code migration (Vals AI) | 57.5% | $60.51 per test | Duration, as printed 2h 51m |
| ProgramBench (Vals AI) | 3.0% | $60.29 per test | Duration, as printed 2h 55m |
| SREBench (Vals AI) | 12.2% | $23.63 per test | Duration, as printed 1h 21m |
|---|---|---|---|
| IOI (Vals AI) | 84.3% | $16.48 per test | Duration, as printed 56m 42s |
| Terminal-Bench 2.1 (Vals AI) | 84.6% | $0.89 per test | Duration, as printed 12m 33s |
| Vibe Code Bench 1-100 (Vals AI) | 28.5% | $41.49 per test | Duration, as printed 1h 22m |
| SkillsBench (Vals AI) | 60.4% | $2.51 per test | Duration, as printed 8m 25s |
| CyberBench (Vals AI) | 65.4% | $2.87 per test | Duration, as printed 19m 25s |
| Finance Agent (Vals AI) | 58.6% | $5.12 per test | Duration, as printed 9m 58s |
| Tax Agent Bench (Vals AI) | 45.5% | $5.14 per test | Duration, as printed 16m 48s |
| Legal Research Bench (Vals AI) | 55.3% | $6.76 per test | Duration, as printed 31m 01s |
| Excel Modeling Benchmark (Vals AI) | 73.6% | $6.07 per test | Duration, as printed 25m 59s |
| BioMysteryBench (Vals AI) | 79.3% | $3.29 per test | Duration, as printed 36m 36s |
| Terminal-Bench-Science (Vals AI) | 27.1% | $32.54 per test | Duration, as printed 2h 12m |
| Vals Science Index | 47.9% | $13.04 per test | Duration, as printed 1h 02m |
| Public Benefits Bench (Vals AI) | 76.9% | $3.95 per test | Nothing else |
| MysteryMechanism (Vals AI) | 37.4% | $3.28 per test | Duration, as printed 16m 53s |
| Vals Multimodal Index | 73.9% | $6.14 per test | Duration, as printed 14m 14s |
| DeepSWE | 73.6% | $11.8376 mean cost per task | Solved in 4 tries 88.5% · Output tokens per task 117,566 · Agent steps per task 99 |
| FrontierSWE | 52.0% | $196.71 average cost per task | Best of 5 runs 60.7% · Hours per task 16.1 h |
| WeirdML | 91.8% | $4.742 per run | Median lines of code 245 |
| ProofBench | 99.0% | $2.1062 per test | Time per proof 9m 51s |
| ALE-Bench | 2164.6 | $1.8905 per problem | Tokens per problem 78,951 |
| LMArena WebDev | 1689 Elo | Not published | Votes 18,555 · Interval (±) ±6.2 |
| GPQA Diamond | 93.4% | Not published | Latency, as printed 40 s |
| MMLU Pro | 91.6% | Not published | Latency, as printed 9.6 s |
| Design Arena: websites | 1310 Elo | Not published | Battles 10,184 |
| Design Arena: UI components | 1348 Elo | Not published | Battles 1,605 |
| Design Arena: game dev | 1337 Elo | Not published | Battles 3,013 |
| Design Arena: data viz | 1329 Elo | Not published | Battles 1,769 |
| Design Arena: 3D | 1335 Elo | Not published | Battles 3,719 |
| Design Arena: all code categories | 1324 Elo | Not published | Battles 19,145 |
| Design Arena: SVG | 1310 Elo | Not published | Battles 1,700 |
| Design Arena: ASCII art | 1352 Elo | Not published | Battles 227 |
| Design Arena: agents building web apps | 1266 Elo | Not published | Battles 1,860 |
| Design Arena: agents building full-stack apps | 1306 Elo | Not published | Battles 1,195 |
| Design Arena: agents building Android apps | 1267 Elo | Not published | Battles 389 |
| Design Arena: agents building Godot games | 1279 Elo | Not published | Battles 793 |
| Design Arena: agents building games | 1262 Elo | Not published | Battles 782 |
| Design Arena: PowerPoint slides | 1266 Elo | Not published | Battles 605 |
| LiveCodeBench (Vals AI) | 89.0% | Not published | Latency, as printed 59 s |
| MMMU Pro (Vals AI) | 89.9% | Not published | Latency, as printed 30 s |
| SAGE (Vals AI) | 49.4% | Not published | Latency, as printed 56 s |
| LegalBench (Vals AI) | 87.0% | Not published | Latency, as printed 4.4 s |
| CorpFin (Vals AI) | 73.2% | Not published | Latency, as printed 29 s |
| TaxEval (Vals AI) | 75.1% | Not published | Latency, as printed 58 s |
| MortgageTax (Vals AI) | 72.1% | Not published | Latency, as printed 8.0 s |
| MedCode (Vals AI) | 63.6% | Not published | Latency, as printed 25 s |
| MedScribe (Vals AI) | 91.0% | Not published | Latency, as printed 1m 17s |
| APEX-Agents | 65.8% | Not published | Mean score 77.0% |
| OSWorld 2.0 | 31.4% | Not published | With partial credit 68.3% |
| LMArena Text | 1508 Elo | Not published | Votes 32,495 · Interval (±) ±4.8 |
| LMArena Text: coding | 1533 Elo | Not published | Votes 8,148 · Interval (±) ±7.5 |
| LMArena Text: hard prompts | 1526 Elo | Not published | Votes 21,001 · Interval (±) ±5.6 |
| LMArena Text: math | 1532 Elo | Not published | Votes 3,152 · Interval (±) ±11.3 |
| LMArena Text: instruction following | 1518 Elo | Not published | Votes 11,298 · Interval (±) ±6.7 |
| LMArena Text: creative writing | 1492 Elo | Not published | Votes 7,375 · Interval (±) ±8.2 |
| LMArena Vision | 1320 Elo | Not published | Votes 17,743 · Interval (±) ±6.6 |
| LMArena Text: English | 1507 Elo | Not published | Votes 13,105 · Interval (±) ±6.3 |
| LMArena Text: non-English | 1500 Elo | Not published | Votes 19,383 · Interval (±) ±5.6 |
| LMArena Text: Chinese | 1573 Elo | Not published | Votes 2,580 · Interval (±) ±12.6 |
| LMArena Text: German | 1526 Elo | Not published | Votes 554 · Interval (±) ±26.1 |
| LMArena Text: Japanese | 1515 Elo | Not published | Votes 554 · Interval (±) ±27.6 |
| LMArena Text: Korean | 1521 Elo | Not published | Votes 637 · Interval (±) ±24.4 |
| LMArena Text: French | 1520 Elo | Not published | Votes 2,058 · Interval (±) ±14.9 |
| LMArena Text: Spanish | 1519 Elo | Not published | Votes 942 · Interval (±) ±20.2 |
| LMArena Text: Russian | 1507 Elo | Not published | Votes 3,918 · Interval (±) ±10.1 |
| LMArena Text: Polish | 1520 Elo | Not published | Votes 507 · Interval (±) ±25.7 |
| LMArena Text: multi-turn | 1499 Elo | Not published | Votes 4,900 · Interval (±) ±9.1 |
| LMArena Text: longer queries | 1516 Elo | Not published | Votes 15,315 · Interval (±) ±6.3 |
| LMArena Text: expert | 1555 Elo | Not published | Votes 7,467 · Interval (±) ±8.1 |
| LMArena Text: hard prompts in English | 1523 Elo | Not published | Votes 8,411 · Interval (±) ±7.4 |
| LMArena Text: software and IT | 1527 Elo | Not published | Votes 24,848 · Interval (±) ±5.4 |
| LMArena Text: mathematical work | 1544 Elo | Not published | Votes 3,767 · Interval (±) ±10.7 |
| LMArena Text: science | 1531 Elo | Not published | Votes 5,481 · Interval (±) ±8.6 |
| LMArena Text: medicine and healthcare | 1526 Elo | Not published | Votes 2,458 · Interval (±) ±12.8 |
| LMArena Text: legal and government | 1529 Elo | Not published | Votes 2,803 · Interval (±) ±11.9 |
| LMArena Text: business and finance | 1501 Elo | Not published | Votes 6,053 · Interval (±) ±8.4 |
| LMArena Text: writing and language | 1498 Elo | Not published | Votes 9,383 · Interval (±) ±7.3 |
| LMArena Text: entertainment and media | 1480 Elo | Not published | Votes 8,667 · Interval (±) ±7.6 |
| LMArena WebDev: React | 1711 Elo | Not published | Votes 12,036 · Interval (±) ±7.3 |
| LMArena WebDev: HTML | 1680 Elo | Not published | Votes 2,295 · Interval (±) ±14.7 |
| LMArena WebDev: from an image | 1662 Elo | Not published | Votes 4,671 · Interval (±) ±9.8 |
| LMArena Vision: English | 1315 Elo | Not published | Votes 6,237 · Interval (±) ±9.3 |
| LMArena Vision: Chinese | 1400 Elo | Not published | Votes 1,037 · Interval (±) ±20.2 |
| LMArena Vision: reading text | 1329 Elo | Not published | Votes 12,218 · Interval (±) ±6.9 |
| LMArena Vision: diagrams | 1348 Elo | Not published | Votes 4,520 · Interval (±) ±9.7 |
| LMArena Vision: homework | 1338 Elo | Not published | Votes 1,899 · Interval (±) ±14.0 |
| LMArena Vision: humor | 1293 Elo | Not published | Votes 876 · Interval (±) ±20.8 |
| LMArena Vision: creative writing | 1313 Elo | Not published | Votes 1,633 · Interval (±) ±15.7 |
| LMArena Search | 1242 Elo | Not published | Votes 13,285 · Interval (±) ±6.9 |
| LMArena Document | 1516 Elo | Not published | Votes 8,794 · Interval (±) ±7.0 |