As of October 20, 2026, Anthropic Claude Opus 4.8 ranks #21 of 213 models overall with 41.8 on the Artificial Analysis Intelligence Index. Its strongest category is knowledge, where it ranks #8 of 147. Anthropic Claude Opus 4.8 costs $5.00 per million input tokens and $25.00 per million output tokens. It was released on May 27, 2026.
Its output price ranks 327 of 349 priced models, counting from the cheapest.
Claude Opus 4.8 is Anthropic's most capable generally available model in the Opus family. It supports text, image, and file inputs with text output, with reasoning support and a 1M-token...
anthropic/claude-opus-4.8 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, IOI (Vals AI), SWE-bench Multimodal (Vals AI), Vibe Code Bench 1-100 (Vals AI), CyberBench (Vals AI), LiveCodeBench (Artificial Analysis run), Terminal-Bench, FrontierSWE, MirrorCode, Cybench, ALE-Bench, LMArena WebDev: from an image
Not measured on Design Arena: spreadsheets, SREBench (Vals AI), Harvey's Legal Agent Benchmark (Vals AI), BioMysteryBench (Vals AI), Vals Science Index, CUA-bench (Vals AI), Robo-bench (Vals AI), METR time horizons, GDPval, BALROG, TheAgentCompany, OSWorld, SpireClimb
Not measured on MysteryMechanism (Vals AI), 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, Fiction.LiveBench, Creative writing (Lech Mazur), CL-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 | 77.3% | 20% |
| LMArena WebDevCoding | 1556 | 15% |
| Vals IndexGeneral | Not measured | Not in index |
| GPQA DiamondReasoning | 92.4% | Not in index |
| AIMEMath | Not measured | Not in index |
| MMLU ProKnowledge | 89.6% | Not in index |
| AA Intelligence IndexIntelligence | 41.8 | Not in index |
| AA Coding IndexCoding | 74.3 | Not in index |
| AA Agentic IndexAgentic work | 41.9 | Not in index |
| Design Arena: websitesWeb design | 1259 | Not in index |
| Design Arena: UI componentsWeb design | 1258 | Not in index |
| Design Arena: game devWeb design | 1263 | Not in index |
| Design Arena: data vizWeb design | 1239 | Not in index |
| Design Arena: 3DWeb design | 1223 | Not in index |
| Design Arena: all code categoriesWeb design | 1255 | Not in index |
| Design Arena: SVGWeb design | 1193 | Not in index |
| Design Arena: ASCII artWeb design | 1277 | Not in index |
| Design Arena: agents building web appsAgentic work | 1232 | Not in index |
| Design Arena: agents building full-stack appsAgentic work | 1249 | Not in index |
| Design Arena: agents building mobile appsAgentic work | 1221 | Not in index |
| Design Arena: agents building Android appsAgentic work | 1247 | Not in index |
| Design Arena: agents building Godot gamesAgentic work | 1231 | Not in index |
| Design Arena: agents building gamesAgentic work | 1238 | Not in index |
| Design Arena: HTML slidesAgentic work | 1221 | Not in index |
| Design Arena: PowerPoint slidesAgentic work | 1227 | 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 | 89.2% | Not in index |
| LiveBench data analysisGeneral | 66.0% | Not in index |
| LiveBench researchAgentic work | 81.8% | Not in index |
| LiveBench browserAgentic work | 96.0% | Not in index |
| LiveBench long agenticAgentic work | 48.3% | Not in index |
| LiveBench designWeb design | 78.8% | Not in index |
| LiveCodeBench (Vals AI)Coding | 87.8% | Not in index |
| SWE-bench Verified (Vals AI)Coding | 88.6% | Not in index |
| Terminal-Bench 4 (Vals AI)Coding | 23.2% | Not in index |
| Vibe Code Bench (Vals AI)Coding | 82.7% | Not in index |
| Code migration (Vals AI)Coding | 47.3% | Not in index |
| ProgramBench (Vals AI)Coding | 1.0% | 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 | 71.9% | 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 | 59.2% | Not in index |
| CyberBench (Vals AI)Coding | Not measured | Not in index |
| Finance Agent (Vals AI)Agentic work | 53.9% | Not in index |
| Tax Agent Bench (Vals AI)Agentic work | 30.0% | Not in index |
| Legal Research Bench (Vals AI)Agentic work | 43.8% | Not in index |
| Harvey's Legal Agent Benchmark (Vals AI)Agentic work | Not measured | Not in index |
| Excel Modeling Benchmark (Vals AI)Agentic work | 69.4% | Not in index |
| BioMysteryBench (Vals AI)Agentic work | Not measured | Not in index |
| Terminal-Bench-Science (Vals AI)Agentic work | 4.3% | Not in index |
| Vals Science IndexAgentic work | Not measured | Not in index |
| Time Horizon Index (Vals AI)Agentic work | 11.8% | 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 | 68.1% | Not in index |
| MysteryMechanism (Vals AI)Reasoning | Not measured | Not in index |
| MMMU Pro (Vals AI)Reasoning | 86.6% | 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 | 54.8% | Not in index |
| LegalBench (Vals AI)Knowledge | 83.6% | Not in index |
| CaseLaw (Vals AI)Knowledge | Not measured | Not in index |
| CorpFin (Vals AI)Knowledge | 66.7% | Not in index |
| TaxEval (Vals AI)Knowledge | 75.6% | Not in index |
| MortgageTax (Vals AI)Knowledge | 69.9% | Not in index |
| MedQA (Vals AI)Knowledge | Not measured | Not in index |
| MedCode (Vals AI)Knowledge | 53.2% | Not in index |
| MedScribe (Vals AI)General | 85.8% | Not in index |
| Vals Multimodal IndexGeneral | 70.9% | Not in index |
| AA Math IndexMath | Not measured | Not in index |
| GPQA Diamond (Artificial Analysis run)Reasoning | 92.0% | Not in index |
| Humanity's Last Exam (Artificial Analysis run)Reasoning | 48.7% | 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 | 54.4% | Not in index |
| Terminal-Bench Hard (Artificial Analysis run)Coding | 58.3% | Not in index |
| IFBenchGeneral | 62.2% | Not in index |
| Long context reasoning (AA-LCR)General | 77.7% | Not in index |
| τ²-Bench TelecomAgentic work | 94.4% | Not in index |
| AIME 2025 (Artificial Analysis run)Math | Not measured | Not in index |
| Terminal-BenchCoding | Not measured | Not in index |
| DeepSWECoding | 59.0% | Not in index |
| FrontierCodeCoding | 46.5% | Not in index |
| FrontierSWECoding | Not measured | Not in index |
| GSO-BenchCoding | 47.1% | Not in index |
| WeirdMLCoding | 82.9% | Not in index |
| MirrorCodeCoding | Not measured | Not in index |
| APEX-AgentsAgentic work | 48.9% | Not in index |
| METR time horizonsAgentic work | Not measured | Not in index |
| Remote Labor IndexAgentic work | 8.3% | Not in index |
| GDPvalAgentic work | Not measured | Not in index |
| OSWorld 2.0Agentic work | 20.6% | Not in index |
| BALROGAgentic work | Not measured | Not in index |
| DeepResearch BenchAgentic work | 50.2% | Not in index |
| PostTrainBenchAgentic work | 33.8% | Not in index |
| GPQA Diamond (Epoch AI run)Reasoning | 91.0% | Not in index |
| ARC-AGIReasoning | 92.5% | Not in index |
| ARC-AGI-2Reasoning | 72.1% | Not in index |
| Humanity's Last ExamReasoning | Not measured | Not in index |
| SimpleBenchReasoning | 64.8% | Not in index |
| Chess puzzlesReasoning | 52.0% | Not in index |
| Mystery game puzzlesReasoning | 36.0% | Not in index |
| EBR-benchReasoning | 28.6% | Not in index |
| OTIS Mock AIMEMath | 98.3% | Not in index |
| FrontierMath, tiers 1 to 3Math | 80.0% | Not in index |
| FrontierMath, tier 4Math | 56.1% | Not in index |
| ProofBenchMath | 69.0% | Not in index |
| MATH level 5Math | Not measured | Not in index |
| GSM8KMath | Not measured | Not in index |
| SimpleQA VerifiedKnowledge | 53.0% | Not in index |
| MMLUKnowledge | Not measured | Not in index |
| GeoBenchKnowledge | Not measured | Not in index |
| DTBenchGeneral | 94.9% | Not in index |
| LMCAGeneral | 57.5% | 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 | 87.5% | Not in index |
| Furniture assemblyGeneral | 42.5% | 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 | Not measured | Not in index |
| Vending-Bench 2Agentic work | $5,787 | Not in index |
| Epoch Capabilities IndexIntelligence | 158.3 | Not in index |
| LMArena TextGeneral | 1461 | Not in index |
| LMArena Text: codingCoding | 1491 | Not in index |
| LMArena Text: hard promptsReasoning | 1482 | Not in index |
| LMArena Text: mathMath | 1486 | Not in index |
| LMArena Text: instruction followingGeneral | 1476 | Not in index |
| LMArena Text: creative writingGeneral | 1454 | Not in index |
| LMArena VisionGeneral | 1294 | Not in index |
| LMArena Text: EnglishGeneral | 1469 | Not in index |
| LMArena Text: non-EnglishGeneral | 1450 | Not in index |
| LMArena Text: ChineseGeneral | 1507 | Not in index |
| LMArena Text: GermanGeneral | 1472 | Not in index |
| LMArena Text: JapaneseGeneral | 1441 | Not in index |
| LMArena Text: KoreanGeneral | 1432 | Not in index |
| LMArena Text: FrenchGeneral | 1481 | Not in index |
| LMArena Text: SpanishGeneral | 1465 | Not in index |
| LMArena Text: RussianGeneral | 1474 | Not in index |
| LMArena Text: PolishGeneral | 1459 | Not in index |
| LMArena Text: multi-turnGeneral | 1475 | Not in index |
| LMArena Text: longer queriesGeneral | 1484 | Not in index |
| LMArena Text: expertReasoning | 1503 | Not in index |
| LMArena Text: hard prompts in EnglishReasoning | 1487 | Not in index |
| LMArena Text: software and ITCoding | 1488 | Not in index |
| LMArena Text: mathematical workMath | 1497 | Not in index |
| LMArena Text: scienceKnowledge | 1477 | Not in index |
| LMArena Text: medicine and healthcareKnowledge | 1464 | Not in index |
| LMArena Text: legal and governmentKnowledge | 1477 | Not in index |
| LMArena Text: business and financeKnowledge | 1458 | Not in index |
| LMArena Text: writing and languageGeneral | 1461 | Not in index |
| LMArena Text: entertainment and mediaGeneral | 1441 | Not in index |
| LMArena WebDev: ReactCoding | 1557 | Not in index |
| LMArena WebDev: HTMLCoding | 1543 | Not in index |
| LMArena WebDev: from an imageCoding | Not measured | Not in index |
| LMArena Vision: EnglishGeneral | 1293 | Not in index |
| LMArena Vision: ChineseGeneral | 1346 | Not in index |
| LMArena Vision: reading textGeneral | 1303 | Not in index |
| LMArena Vision: diagramsReasoning | 1315 | Not in index |
| LMArena Vision: homeworkReasoning | 1337 | Not in index |
| LMArena Vision: humorGeneral | 1282 | Not in index |
| LMArena Vision: captioningGeneral | Not measured | Not in index |
| LMArena Vision: recognizing thingsGeneral | Not measured | Not in index |
| LMArena Vision: creative writingGeneral | 1301 | Not in index |
| LMArena SearchAgentic work | 1204 | Not in index |
| LMArena DocumentGeneral | 1475 | 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 | 77.3% | $4.1517 per task | Output tokens per task 55,126 |
| LiveBench reasoning | 89.2% | $0.6057 per task | Output tokens per task 23,900 |
| LiveBench data analysis | 66.0% | $0.6456 per task | Output tokens per task 25,286 |
| LiveBench research | 81.8% | $6.2353 per task | Output tokens per task 64,378 |
| LiveBench browser | 96.0% | $8.8717 per task | Output tokens per task 52,703 |
| LiveBench long agentic | 48.3% | $51.9696 per task | Output tokens per task 522,691 |
| LiveBench design | 78.8% | $6.4503 per task | Output tokens per task 81,857 |
| SWE-bench Verified (Vals AI) | 88.6% | $1.92 per test | Duration, as printed 9m 27s |
| Terminal-Bench 4 (Vals AI) | 23.2% | $17.14 per test | Duration, as printed 1h 11m |
| Vibe Code Bench (Vals AI) | 82.7% | $26.88 per test | Duration, as printed 1h 16m |
| Code migration (Vals AI) | 47.3% | $30.51 per test | Duration, as printed 1h 15m |
| ProgramBench (Vals AI) | 1.0% | $31.27 per test | Duration, as printed 1h 32m |
| Terminal-Bench 2.1 (Vals AI) | 71.9% | $2.41 per test | Duration, as printed 15m 30s |
|---|---|---|---|
| SkillsBench (Vals AI) | 59.2% | $4.77 per test | Duration, as printed 15m 30s |
| Finance Agent (Vals AI) | 53.9% | $4.22 per test | Duration, as printed 9m 07s |
| Tax Agent Bench (Vals AI) | 30.0% | $1.69 per test | Duration, as printed 7m 59s |
| Legal Research Bench (Vals AI) | 43.8% | $2.82 per test | Duration, as printed 11m 54s |
| Excel Modeling Benchmark (Vals AI) | 69.4% | $12.06 per test | Duration, as printed 43m 52s |
| Terminal-Bench-Science (Vals AI) | 4.3% | $23.14 per test | Duration, as printed 1h 55m |
| Public Benefits Bench (Vals AI) | 68.1% | $1.89 per test | Nothing else |
| Vals Multimodal Index | 70.9% | $5.46 per test | Duration, as printed 16m 20s |
| DeepSWE | 59.0% | $13.2226 mean cost per task | Solved in 4 tries 79.3% · Output tokens per task 135,032 · Agent steps per task 120 |
| WeirdML | 82.9% | $2.3498 per run | Median lines of code 129 |
| ARC-AGI | 92.5% | $2.332 per task | Nothing else |
| ARC-AGI-2 | 72.1% | $2.7425 per task | Nothing else |
| ProofBench | 69.0% | $2.2931 per test | Time per proof 19m 26s |
| Surface Evolver Bench | 87.5% | $21.9616 of the run | Pass rate 68.8% · Tokens for the run 2.7M |
| LMArena WebDev | 1556 Elo | Not published | Votes 18,493 · Interval (±) ±5.8 |
| GPQA Diamond | 92.4% | Not published | Latency, as printed 2m 14s |
| MMLU Pro | 89.6% | Not published | Latency, as printed 23 s |
| Design Arena: websites | 1259 Elo | Not published | Battles 19,529 |
| Design Arena: UI components | 1258 Elo | Not published | Battles 2,340 |
| Design Arena: game dev | 1263 Elo | Not published | Battles 4,894 |
| Design Arena: data viz | 1239 Elo | Not published | Battles 1,843 |
| Design Arena: 3D | 1223 Elo | Not published | Battles 7,335 |
| Design Arena: all code categories | 1255 Elo | Not published | Battles 32,708 |
| Design Arena: SVG | 1193 Elo | Not published | Battles 2,872 |
| Design Arena: ASCII art | 1277 Elo | Not published | Battles 443 |
| Design Arena: agents building web apps | 1232 Elo | Not published | Battles 3,664 |
| Design Arena: agents building full-stack apps | 1249 Elo | Not published | Battles 2,700 |
| Design Arena: agents building mobile apps | 1221 Elo | Not published | Battles 1,254 |
| Design Arena: agents building Android apps | 1247 Elo | Not published | Battles 938 |
| Design Arena: agents building Godot games | 1231 Elo | Not published | Battles 1,659 |
| Design Arena: agents building games | 1238 Elo | Not published | Battles 1,375 |
| Design Arena: HTML slides | 1221 Elo | Not published | Battles 3,664 |
| Design Arena: PowerPoint slides | 1227 Elo | Not published | Battles 1,493 |
| LiveCodeBench (Vals AI) | 87.8% | Not published | Latency, as printed 2m 40s |
| MMMU Pro (Vals AI) | 86.6% | Not published | Latency, as printed 49 s |
| SAGE (Vals AI) | 54.8% | Not published | Latency, as printed 3m 06s |
| LegalBench (Vals AI) | 83.6% | Not published | Latency, as printed 3.1 s |
| CorpFin (Vals AI) | 66.7% | Not published | Latency, as printed 20 s |
| TaxEval (Vals AI) | 75.6% | Not published | Latency, as printed 1m 10s |
| MortgageTax (Vals AI) | 69.9% | Not published | Latency, as printed 21 s |
| MedCode (Vals AI) | 53.2% | Not published | Latency, as printed 1m 46s |
| MedScribe (Vals AI) | 85.8% | Not published | Latency, as printed 1m 22s |
| APEX-Agents | 48.9% | Not published | Mean score 64.4% |
| OSWorld 2.0 | 20.6% | Not published | With partial credit 54.8% |
| LMArena Text | 1461 Elo | Not published | Votes 64,100 · Interval (±) ±3.9 |
| LMArena Text: coding | 1491 Elo | Not published | Votes 17,427 · Interval (±) ±5.8 |
| LMArena Text: hard prompts | 1482 Elo | Not published | Votes 42,534 · Interval (±) ±4.5 |
| LMArena Text: math | 1486 Elo | Not published | Votes 2,969 · Interval (±) ±11.2 |
| LMArena Text: instruction following | 1476 Elo | Not published | Votes 22,679 · Interval (±) ±5.3 |
| LMArena Text: creative writing | 1454 Elo | Not published | Votes 12,797 · Interval (±) ±6.5 |
| LMArena Vision | 1294 Elo | Not published | Votes 18,303 · Interval (±) ±6.5 |
| LMArena Text: English | 1469 Elo | Not published | Votes 28,033 · Interval (±) ±5.0 |
| LMArena Text: non-English | 1450 Elo | Not published | Votes 36,060 · Interval (±) ±4.7 |
| LMArena Text: Chinese | 1507 Elo | Not published | Votes 4,397 · Interval (±) ±9.6 |
| LMArena Text: German | 1472 Elo | Not published | Votes 1,077 · Interval (±) ±18.8 |
| LMArena Text: Japanese | 1441 Elo | Not published | Votes 892 · Interval (±) ±21.9 |
| LMArena Text: Korean | 1432 Elo | Not published | Votes 1,107 · Interval (±) ±19.3 |
| LMArena Text: French | 1481 Elo | Not published | Votes 2,188 · Interval (±) ±14.3 |
| LMArena Text: Spanish | 1465 Elo | Not published | Votes 1,865 · Interval (±) ±14.7 |
| LMArena Text: Russian | 1474 Elo | Not published | Votes 7,149 · Interval (±) ±7.7 |
| LMArena Text: Polish | 1459 Elo | Not published | Votes 1,090 · Interval (±) ±17.6 |
| LMArena Text: multi-turn | 1475 Elo | Not published | Votes 11,189 · Interval (±) ±6.7 |
| LMArena Text: longer queries | 1484 Elo | Not published | Votes 30,215 · Interval (±) ±5.1 |
| LMArena Text: expert | 1503 Elo | Not published | Votes 7,067 · Interval (±) ±7.8 |
| LMArena Text: hard prompts in English | 1487 Elo | Not published | Votes 18,817 · Interval (±) ±5.7 |
| LMArena Text: software and IT | 1488 Elo | Not published | Votes 25,123 · Interval (±) ±5.2 |
| LMArena Text: mathematical work | 1497 Elo | Not published | Votes 3,480 · Interval (±) ±10.7 |
| LMArena Text: science | 1477 Elo | Not published | Votes 10,441 · Interval (±) ±6.7 |
| LMArena Text: medicine and healthcare | 1464 Elo | Not published | Votes 4,774 · Interval (±) ±9.3 |
| LMArena Text: legal and government | 1477 Elo | Not published | Votes 5,534 · Interval (±) ±8.7 |
| LMArena Text: business and finance | 1458 Elo | Not published | Votes 12,750 · Interval (±) ±6.3 |
| LMArena Text: writing and language | 1461 Elo | Not published | Votes 17,290 · Interval (±) ±5.8 |
| LMArena Text: entertainment and media | 1441 Elo | Not published | Votes 16,188 · Interval (±) ±6.0 |
| LMArena WebDev: React | 1557 Elo | Not published | Votes 11,873 · Interval (±) ±6.6 |
| LMArena WebDev: HTML | 1543 Elo | Not published | Votes 2,270 · Interval (±) ±13.7 |
| LMArena Vision: English | 1293 Elo | Not published | Votes 7,311 · Interval (±) ±9.1 |
| LMArena Vision: Chinese | 1346 Elo | Not published | Votes 1,131 · Interval (±) ±19.6 |
| LMArena Vision: reading text | 1303 Elo | Not published | Votes 12,994 · Interval (±) ±6.6 |
| LMArena Vision: diagrams | 1315 Elo | Not published | Votes 4,883 · Interval (±) ±9.5 |
| LMArena Vision: homework | 1337 Elo | Not published | Votes 2,077 · Interval (±) ±13.5 |
| LMArena Vision: humor | 1282 Elo | Not published | Votes 756 · Interval (±) ±22.2 |
| LMArena Vision: creative writing | 1301 Elo | Not published | Votes 1,398 · Interval (±) ±16.8 |
| LMArena Search | 1204 Elo | Not published | Votes 106,304 · Interval (±) ±5.6 |
| LMArena Document | 1475 Elo | Not published | Votes 11,551 · Interval (±) ±6.9 |