As of October 20, 2026, Anthropic Claude Fable 5 ranks #8 of 213 models overall with 49.6 on the Artificial Analysis Intelligence Index. Its strongest category is math, where it ranks #1 of 116. Anthropic Claude Fable 5 costs $10.00 per million input tokens and $50.00 per million output tokens. It was released on June 9, 2026.
Its output price ranks 337 of 349 priced models, counting from the cheapest.
Claude Fable 5 is a Mythos-class model from Anthropic, built for autonomous knowledge work and coding. It supports text, image, and file inputs with text output, with reasoning support and...
anthropic/claude-fable-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, IOI (Vals AI), SWE-bench Multimodal (Vals AI), Vibe Code Bench 1-100 (Vals AI), SkillsBench (Vals AI), CyberBench (Vals AI), LiveCodeBench (Artificial Analysis run), Terminal-Bench, Cybench
Not measured on Design Arena: spreadsheets, SREBench (Vals AI), Harvey's Legal Agent Benchmark (Vals AI), BioMysteryBench (Vals AI), Vals Science Index, Time Horizon Index (Vals AI), CUA-bench (Vals AI), Robo-bench (Vals AI), METR time horizons, GDPval, OSWorld 2.0, BALROG, DeepResearch Bench, 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 | 98.3% | 20% |
| LMArena WebDevCoding | 1624 | 15% |
| Vals IndexGeneral | Not measured | Not in index |
| GPQA DiamondReasoning | 93.2% | Not in index |
| AIMEMath | Not measured | Not in index |
| MMLU ProKnowledge | 91.5% | Not in index |
| AA Intelligence IndexIntelligence | 49.6 | Not in index |
| AA Coding IndexCoding | 76.5 | Not in index |
| AA Agentic IndexAgentic work | 50.7 | Not in index |
| Design Arena: websitesWeb design | 1296 | Not in index |
| Design Arena: UI componentsWeb design | 1319 | Not in index |
| Design Arena: game devWeb design | 1335 | Not in index |
| Design Arena: data vizWeb design | 1304 | Not in index |
| Design Arena: 3DWeb design | 1319 | Not in index |
| Design Arena: all code categoriesWeb design | 1311 | Not in index |
| Design Arena: SVGWeb design | 1302 | Not in index |
| Design Arena: ASCII artWeb design | 1329 | Not in index |
| Design Arena: agents building web appsAgentic work | 1261 | Not in index |
| Design Arena: agents building full-stack appsAgentic work | 1280 | Not in index |
| Design Arena: agents building mobile appsAgentic work | 1263 | Not in index |
| Design Arena: agents building Android appsAgentic work | 1298 | Not in index |
| Design Arena: agents building Godot gamesAgentic work | 1292 | Not in index |
| Design Arena: agents building gamesAgentic work | 1285 | Not in index |
| Design Arena: HTML slidesAgentic work | 1277 | Not in index |
| Design Arena: PowerPoint slidesAgentic work | 1295 | 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 | 89.7% | Not in index |
| LiveBench data analysisGeneral | 80.5% | Not in index |
| LiveBench researchAgentic work | 86.9% | Not in index |
| LiveBench browserAgentic work | 92.0% | Not in index |
| LiveBench long agenticAgentic work | 53.2% | Not in index |
| LiveBench designWeb design | 84.7% | Not in index |
| LiveCodeBench (Vals AI)Coding | 89.8% | Not in index |
| SWE-bench Verified (Vals AI)Coding | 95.0% | Not in index |
| Terminal-Bench 4 (Vals AI)Coding | 41.4% | Not in index |
| Vibe Code Bench (Vals AI)Coding | 90.3% | Not in index |
| Code migration (Vals AI)Coding | 55.1% | Not in index |
| ProgramBench (Vals AI)Coding | 2.0% | 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 | 80.5% | 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 | 56.3% | Not in index |
| Tax Agent Bench (Vals AI)Agentic work | 38.3% | Not in index |
| Legal Research Bench (Vals AI)Agentic work | 49.5% | Not in index |
| Harvey's Legal Agent Benchmark (Vals AI)Agentic work | Not measured | Not in index |
| Excel Modeling Benchmark (Vals AI)Agentic work | 73.7% | Not in index |
| BioMysteryBench (Vals AI)Agentic work | Not measured | Not in index |
| Terminal-Bench-Science (Vals AI)Agentic work | 15.7% | 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 | 70.4% | Not in index |
| MysteryMechanism (Vals AI)Reasoning | Not measured | Not in index |
| MMMU Pro (Vals AI)Reasoning | 89.3% | 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 | 51.9% | Not in index |
| LegalBench (Vals AI)Knowledge | 88.6% | Not in index |
| CaseLaw (Vals AI)Knowledge | Not measured | Not in index |
| CorpFin (Vals AI)Knowledge | 71.8% | Not in index |
| TaxEval (Vals AI)Knowledge | 76.9% | Not in index |
| MortgageTax (Vals AI)Knowledge | 68.9% | Not in index |
| MedQA (Vals AI)Knowledge | Not measured | Not in index |
| MedCode (Vals AI)Knowledge | 56.1% | Not in index |
| MedScribe (Vals AI)General | 88.5% | Not in index |
| Vals Multimodal IndexGeneral | 74.2% | Not in index |
| AA Math IndexMath | Not measured | Not in index |
| GPQA Diamond (Artificial Analysis run)Reasoning | 92.6% | Not in index |
| Humanity's Last Exam (Artificial Analysis run)Reasoning | 55.5% | 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 | 61.0% | Not in index |
| Terminal-Bench Hard (Artificial Analysis run)Coding | 62.9% | Not in index |
| IFBenchGeneral | 63.5% | Not in index |
| Long context reasoning (AA-LCR)General | 82.3% | Not in index |
| τ²-Bench TelecomAgentic work | 98.5% | Not in index |
| AIME 2025 (Artificial Analysis run)Math | Not measured | Not in index |
| Terminal-BenchCoding | Not measured | Not in index |
| DeepSWECoding | 69.9% | Not in index |
| FrontierCodeCoding | 53.5% | Not in index |
| FrontierSWECoding | 47.0% | Not in index |
| GSO-BenchCoding | 78.4% | Not in index |
| WeirdMLCoding | 91.9% | Not in index |
| MirrorCodeCoding | 63.9% | Not in index |
| APEX-AgentsAgentic work | 63.6% | Not in index |
| METR time horizonsAgentic work | Not measured | Not in index |
| Remote Labor IndexAgentic work | 16.1% | 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 | Not measured | Not in index |
| PostTrainBenchAgentic work | 41.8% | Not in index |
| GPQA Diamond (Epoch AI run)Reasoning | 85.9% | Not in index |
| ARC-AGIReasoning | 98.5% | Not in index |
| ARC-AGI-2Reasoning | 89.2% | Not in index |
| Humanity's Last ExamReasoning | Not measured | Not in index |
| SimpleBenchReasoning | 81.9% | Not in index |
| Chess puzzlesReasoning | 47.0% | Not in index |
| Mystery game puzzlesReasoning | 52.0% | Not in index |
| EBR-benchReasoning | 39.5% | Not in index |
| OTIS Mock AIMEMath | 100.0% | Not in index |
| FrontierMath, tiers 1 to 3Math | 87.0% | Not in index |
| FrontierMath, tier 4Math | 90.2% | Not in index |
| ProofBenchMath | 95.0% | Not in index |
| MATH level 5Math | Not measured | Not in index |
| GSM8KMath | Not measured | Not in index |
| SimpleQA VerifiedKnowledge | 70.7% | Not in index |
| MMLUKnowledge | Not measured | Not in index |
| GeoBenchKnowledge | Not measured | Not in index |
| DTBenchGeneral | 98.4% | Not in index |
| LMCAGeneral | 61.2% | 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 | 95.0% | Not in index |
| Furniture assemblyGeneral | 35.8% | 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 | 2041.3 | Not in index |
| Vending-Bench 2Agentic work | $5,680 | Not in index |
| Epoch Capabilities IndexIntelligence | 162.1 | Not in index |
| LMArena TextGeneral | 1491 | Not in index |
| LMArena Text: codingCoding | 1518 | Not in index |
| LMArena Text: hard promptsReasoning | 1507 | Not in index |
| LMArena Text: mathMath | 1519 | Not in index |
| LMArena Text: instruction followingGeneral | 1502 | Not in index |
| LMArena Text: creative writingGeneral | 1494 | Not in index |
| LMArena VisionGeneral | 1325 | Not in index |
| LMArena Text: EnglishGeneral | 1499 | Not in index |
| LMArena Text: non-EnglishGeneral | 1481 | Not in index |
| LMArena Text: ChineseGeneral | 1542 | Not in index |
| LMArena Text: GermanGeneral | 1487 | Not in index |
| LMArena Text: JapaneseGeneral | 1506 | Not in index |
| LMArena Text: KoreanGeneral | 1491 | Not in index |
| LMArena Text: FrenchGeneral | 1504 | Not in index |
| LMArena Text: SpanishGeneral | 1496 | Not in index |
| LMArena Text: RussianGeneral | 1503 | Not in index |
| LMArena Text: PolishGeneral | 1493 | Not in index |
| LMArena Text: multi-turnGeneral | 1505 | Not in index |
| LMArena Text: longer queriesGeneral | 1510 | Not in index |
| LMArena Text: expertReasoning | 1535 | Not in index |
| LMArena Text: hard prompts in EnglishReasoning | 1510 | Not in index |
| LMArena Text: software and ITCoding | 1512 | Not in index |
| LMArena Text: mathematical workMath | 1515 | Not in index |
| LMArena Text: scienceKnowledge | 1506 | Not in index |
| LMArena Text: medicine and healthcareKnowledge | 1481 | Not in index |
| LMArena Text: legal and governmentKnowledge | 1499 | Not in index |
| LMArena Text: business and financeKnowledge | 1480 | Not in index |
| LMArena Text: writing and languageGeneral | 1501 | Not in index |
| LMArena Text: entertainment and mediaGeneral | 1482 | Not in index |
| LMArena WebDev: ReactCoding | 1631 | Not in index |
| LMArena WebDev: HTMLCoding | 1651 | Not in index |
| LMArena WebDev: from an imageCoding | 1623 | Not in index |
| LMArena Vision: EnglishGeneral | 1323 | Not in index |
| LMArena Vision: ChineseGeneral | 1373 | Not in index |
| LMArena Vision: reading textGeneral | 1337 | Not in index |
| LMArena Vision: diagramsReasoning | 1357 | Not in index |
| LMArena Vision: homeworkReasoning | 1361 | Not in index |
| LMArena Vision: humorGeneral | 1341 | Not in index |
| LMArena Vision: captioningGeneral | Not measured | Not in index |
| LMArena Vision: recognizing thingsGeneral | Not measured | Not in index |
| LMArena Vision: creative writingGeneral | 1338 | Not in index |
| LMArena SearchAgentic work | 1229 | Not in index |
| LMArena DocumentGeneral | 1496 | 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 | 98.3% | $8.9273 per task | Output tokens per task 49,492 |
| LiveBench reasoning | 89.7% | $0.6024 per task | Output tokens per task 11,716 |
| LiveBench data analysis | 80.5% | $1.3007 per task | Output tokens per task 25,207 |
| LiveBench research | 86.9% | $17.2743 per task | Output tokens per task 71,540 |
| LiveBench browser | 92.0% | $10.3016 per task | Output tokens per task 25,561 |
| LiveBench long agentic | 53.2% | $59.7366 per task | Output tokens per task 265,052 |
| LiveBench design | 84.7% | $8.5495 per task | Output tokens per task 63,307 |
| SWE-bench Verified (Vals AI) | 95.0% | $2.05 per test | Duration, as printed 5m 56s |
| Terminal-Bench 4 (Vals AI) | 41.4% | $30.34 per test | Duration, as printed 1h 08m |
| Vibe Code Bench (Vals AI) | 90.3% | $41.71 per test | Duration, as printed 1h 02m |
| Code migration (Vals AI) | 55.1% | $112.10 per test | Duration, as printed 1h 49m |
| ProgramBench (Vals AI) | 2.0% | $75.68 per test | Duration, as printed 2h 37m |
| Terminal-Bench 2.1 (Vals AI) | 80.5% | $1.43 per test | Duration, as printed 8m 25s |
|---|---|---|---|
| Finance Agent (Vals AI) | 56.3% | $8.06 per test | Duration, as printed 10m 11s |
| Tax Agent Bench (Vals AI) | 38.3% | $6.70 per test | Duration, as printed 14m 27s |
| Legal Research Bench (Vals AI) | 49.5% | $9.79 per test | Duration, as printed 22m 18s |
| Excel Modeling Benchmark (Vals AI) | 73.7% | $12.35 per test | Duration, as printed 26m 34s |
| Terminal-Bench-Science (Vals AI) | 15.7% | $51.99 per test | Duration, as printed 1h 59m |
| Public Benefits Bench (Vals AI) | 70.4% | $4.59 per test | Nothing else |
| Vals Multimodal Index | 74.2% | $7.97 per test | Duration, as printed 12m 49s |
| DeepSWE | 69.9% | $13.4145 mean cost per task | Solved in 4 tries 88.5% · Output tokens per task 80,352 · Agent steps per task 68 |
| FrontierSWE | 47.0% | $301.28 average cost per task | Best of 5 runs 61.8% · Hours per task 15.8 h |
| WeirdML | 91.9% | $8.4244 per run | Median lines of code 218 |
| ProofBench | 95.0% | $5.4515 per test | Time per proof 13m 43s |
| Surface Evolver Bench | 95.0% | $19.4352 of the run | Pass rate 87.5% · Tokens for the run 933,342 |
| ALE-Bench | 2041.3 | $2.1088 per problem | Tokens per problem 45,507 |
| LMArena WebDev | 1624 Elo | Not published | Votes 15,899 · Interval (±) ±6.1 |
| GPQA Diamond | 93.2% | Not published | Latency, as printed 1m 40s |
| MMLU Pro | 91.5% | Not published | Latency, as printed 25 s |
| Design Arena: websites | 1296 Elo | Not published | Battles 10,872 |
| Design Arena: UI components | 1319 Elo | Not published | Battles 1,547 |
| Design Arena: game dev | 1335 Elo | Not published | Battles 3,461 |
| Design Arena: data viz | 1304 Elo | Not published | Battles 1,364 |
| Design Arena: 3D | 1319 Elo | Not published | Battles 4,617 |
| Design Arena: all code categories | 1311 Elo | Not published | Battles 20,216 |
| Design Arena: SVG | 1302 Elo | Not published | Battles 2,098 |
| Design Arena: ASCII art | 1329 Elo | Not published | Battles 298 |
| Design Arena: agents building web apps | 1261 Elo | Not published | Battles 2,911 |
| Design Arena: agents building full-stack apps | 1280 Elo | Not published | Battles 2,118 |
| Design Arena: agents building mobile apps | 1263 Elo | Not published | Battles 791 |
| Design Arena: agents building Android apps | 1298 Elo | Not published | Battles 461 |
| Design Arena: agents building Godot games | 1292 Elo | Not published | Battles 1,379 |
| Design Arena: agents building games | 1285 Elo | Not published | Battles 1,428 |
| Design Arena: HTML slides | 1277 Elo | Not published | Battles 2,181 |
| Design Arena: PowerPoint slides | 1295 Elo | Not published | Battles 1,914 |
| LiveCodeBench (Vals AI) | 89.8% | Not published | Latency, as printed 1m 59s |
| MMMU Pro (Vals AI) | 89.3% | Not published | Latency, as printed 1m 01s |
| SAGE (Vals AI) | 51.9% | Not published | Latency, as printed 1m 57s |
| LegalBench (Vals AI) | 88.6% | Not published | Latency, as printed 9.0 s |
| CorpFin (Vals AI) | 71.8% | Not published | Latency, as printed 53 s |
| TaxEval (Vals AI) | 76.9% | Not published | Latency, as printed 57 s |
| MortgageTax (Vals AI) | 68.9% | Not published | Latency, as printed 16 s |
| MedCode (Vals AI) | 56.1% | Not published | Latency, as printed 1m 31s |
| MedScribe (Vals AI) | 88.5% | Not published | Latency, as printed 1m 59s |
| APEX-Agents | 63.6% | Not published | Mean score 74.5% |
| LMArena Text | 1491 Elo | Not published | Votes 42,004 · Interval (±) ±4.3 |
| LMArena Text: coding | 1518 Elo | Not published | Votes 10,844 · Interval (±) ±6.6 |
| LMArena Text: hard prompts | 1507 Elo | Not published | Votes 27,374 · Interval (±) ±4.9 |
| LMArena Text: math | 1519 Elo | Not published | Votes 2,069 · Interval (±) ±13.2 |
| LMArena Text: instruction following | 1502 Elo | Not published | Votes 14,825 · Interval (±) ±6.0 |
| LMArena Text: creative writing | 1494 Elo | Not published | Votes 9,020 · Interval (±) ±7.4 |
| LMArena Vision | 1325 Elo | Not published | Votes 14,714 · Interval (±) ±7.0 |
| LMArena Text: English | 1499 Elo | Not published | Votes 17,924 · Interval (±) ±5.5 |
| LMArena Text: non-English | 1481 Elo | Not published | Votes 24,075 · Interval (±) ±5.0 |
| LMArena Text: Chinese | 1542 Elo | Not published | Votes 3,131 · Interval (±) ±11.2 |
| LMArena Text: German | 1487 Elo | Not published | Votes 650 · Interval (±) ±23.7 |
| LMArena Text: Japanese | 1506 Elo | Not published | Votes 612 · Interval (±) ±25.8 |
| LMArena Text: Korean | 1491 Elo | Not published | Votes 792 · Interval (±) ±22.6 |
| LMArena Text: French | 1504 Elo | Not published | Votes 1,430 · Interval (±) ±17.3 |
| LMArena Text: Spanish | 1496 Elo | Not published | Votes 1,314 · Interval (±) ±17.1 |
| LMArena Text: Russian | 1503 Elo | Not published | Votes 4,719 · Interval (±) ±9.2 |
| LMArena Text: Polish | 1493 Elo | Not published | Votes 623 · Interval (±) ±23.1 |
| LMArena Text: multi-turn | 1505 Elo | Not published | Votes 6,819 · Interval (±) ±7.9 |
| LMArena Text: longer queries | 1510 Elo | Not published | Votes 19,543 · Interval (±) ±5.6 |
| LMArena Text: expert | 1535 Elo | Not published | Votes 4,679 · Interval (±) ±9.3 |
| LMArena Text: hard prompts in English | 1510 Elo | Not published | Votes 11,708 · Interval (±) ±6.4 |
| LMArena Text: software and IT | 1512 Elo | Not published | Votes 15,669 · Interval (±) ±5.7 |
| LMArena Text: mathematical work | 1515 Elo | Not published | Votes 2,424 · Interval (±) ±12.6 |
| LMArena Text: science | 1506 Elo | Not published | Votes 6,883 · Interval (±) ±7.8 |
| LMArena Text: medicine and healthcare | 1481 Elo | Not published | Votes 2,983 · Interval (±) ±11.6 |
| LMArena Text: legal and government | 1499 Elo | Not published | Votes 3,514 · Interval (±) ±10.7 |
| LMArena Text: business and finance | 1480 Elo | Not published | Votes 8,357 · Interval (±) ±7.2 |
| LMArena Text: writing and language | 1501 Elo | Not published | Votes 11,803 · Interval (±) ±6.6 |
| LMArena Text: entertainment and media | 1482 Elo | Not published | Votes 10,958 · Interval (±) ±6.8 |
| LMArena WebDev: React | 1631 Elo | Not published | Votes 11,075 · Interval (±) ±7.1 |
| LMArena WebDev: HTML | 1651 Elo | Not published | Votes 2,175 · Interval (±) ±14.7 |
| LMArena WebDev: from an image | 1623 Elo | Not published | Votes 5,855 · Interval (±) ±8.9 |
| LMArena Vision: English | 1323 Elo | Not published | Votes 5,874 · Interval (±) ±9.7 |
| LMArena Vision: Chinese | 1373 Elo | Not published | Votes 784 · Interval (±) ±22.7 |
| LMArena Vision: reading text | 1337 Elo | Not published | Votes 10,497 · Interval (±) ±7.3 |
| LMArena Vision: diagrams | 1357 Elo | Not published | Votes 3,956 · Interval (±) ±10.3 |
| LMArena Vision: homework | 1361 Elo | Not published | Votes 1,751 · Interval (±) ±14.7 |
| LMArena Vision: humor | 1341 Elo | Not published | Votes 583 · Interval (±) ±25.3 |
| LMArena Vision: creative writing | 1338 Elo | Not published | Votes 1,159 · Interval (±) ±18.6 |
| LMArena Search | 1229 Elo | Not published | Votes 73,596 · Interval (±) ±6.5 |
| LMArena Document | 1496 Elo | Not published | Votes 8,497 · Interval (±) ±7.9 |