As of October 21, 2026, Meta Muse Spark 1.2 ranks #27 of 213 models overall with 39.6 on the Artificial Analysis Intelligence Index. Its strongest category is web design, where it ranks #10 of 133. Meta Muse Spark 1.2 costs $1.25 per million input tokens and $4.25 per million output tokens. It was released on August 5, 2026.
Its output price ranks 246 of 349 priced models, counting from the cheapest.
Muse Spark 1.2 is a reasoning model from Meta, designed for complex agentic tasks. It accepts text, images, video, and PDF documents, returns text, and offers a 1M-token context window....
meta/muse-spark-1.2 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 (full test set), SWE-bench Multimodal, SWE-bench Multilingual, LiveCodeBench (Vals AI), SWE-bench Multimodal (Vals AI), Vibe Code Bench 1-100 (Vals AI), LiveCodeBench (Artificial Analysis run), Terminal-Bench Hard (Artificial Analysis run), Terminal-Bench, DeepSWE, FrontierCode, GSO-Bench, MirrorCode, Cybench, ALE-Bench, LMArena WebDev: from an image
Not measured on Design Arena: agents building Godot games, Design Arena: spreadsheets, Harvey's Legal Agent Benchmark (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, METR time horizons, Remote Labor Index, GDPval, OSWorld 2.0, BALROG, DeepResearch Bench, PostTrainBench, TheAgentCompany, OSWorld, SpireClimb, Vending-Bench 2, LMArena Search
Not measured on GPQA Diamond, MysteryMechanism (Vals AI), GPQA Diamond (Epoch AI run), ARC-AGI, ARC-AGI-2, Humanity's Last Exam, Mystery game puzzles, EBR-bench, VPCT, BIG-Bench Hard, LMArena Vision: homework
Not measured on AIME, MATH 500 (Vals AI), MGSM (Vals AI), AA Math Index, AIME 2025 (Artificial Analysis run), OTIS Mock AIME, FrontierMath, tiers 1 to 3, FrontierMath, tier 4, 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, Furniture assembly, ExploitBench, HellaSwag, WinoGrande, PIQA, CL-bench Life, LMArena Text: German, LMArena Text: Japanese, LMArena Text: Polish, LMArena Vision: Chinese, LMArena Vision: humor, LMArena Vision: captioning, LMArena Vision: recognizing things, LMArena Vision: creative writing, LMArena Document
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 | 78.2% | 20% |
| LMArena WebDevCoding | 1534 | 15% |
| Vals IndexGeneral | Not measured | Not in index |
| GPQA DiamondReasoning | Not measured | Not in index |
| AIMEMath | Not measured | Not in index |
| MMLU ProKnowledge | 88.3% | Not in index |
| AA Intelligence IndexIntelligence | 39.6 | Not in index |
| AA Coding IndexCoding | 72.2 | Not in index |
| AA Agentic IndexAgentic work | 43.2 | Not in index |
| Design Arena: websitesWeb design | 1313 | Not in index |
| Design Arena: UI componentsWeb design | 1300 | Not in index |
| Design Arena: game devWeb design | 1302 | Not in index |
| Design Arena: data vizWeb design | 1334 | Not in index |
| Design Arena: 3DWeb design | 1301 | Not in index |
| Design Arena: all code categoriesWeb design | 1313 | Not in index |
| Design Arena: SVGWeb design | 1285 | Not in index |
| Design Arena: ASCII artWeb design | 1284 | Not in index |
| Design Arena: agents building web appsAgentic work | 1222 | Not in index |
| Design Arena: agents building full-stack appsAgentic work | 1210 | Not in index |
| Design Arena: agents building mobile appsAgentic work | 1182 | Not in index |
| Design Arena: agents building Android appsAgentic work | 1228 | Not in index |
| Design Arena: agents building Godot gamesAgentic work | Not measured | Not in index |
| Design Arena: agents building gamesAgentic work | 1179 | Not in index |
| Design Arena: HTML slidesAgentic work | 1135 | Not in index |
| Design Arena: PowerPoint slidesAgentic work | 1198 | 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 | 90.0% | Not in index |
| LiveBench data analysisGeneral | 76.5% | Not in index |
| LiveBench researchAgentic work | 67.7% | Not in index |
| LiveBench browserAgentic work | 36.0% | Not in index |
| LiveBench long agenticAgentic work | 21.3% | Not in index |
| LiveBench designWeb design | 67.1% | Not in index |
| LiveCodeBench (Vals AI)Coding | Not measured | Not in index |
| SWE-bench Verified (Vals AI)Coding | 86.6% | Not in index |
| Terminal-Bench 4 (Vals AI)Coding | 6.1% | Not in index |
| Vibe Code Bench (Vals AI)Coding | 79.1% | Not in index |
| Code migration (Vals AI)Coding | 29.9% | Not in index |
| ProgramBench (Vals AI)Coding | 0.5% | Not in index |
| SREBench (Vals AI)Agentic work | 0.0% | Not in index |
| IOI (Vals AI)Coding | 21.8% | Not in index |
| Terminal-Bench 2.1 (Vals AI)Coding | 69.7% | 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 | 53.0% | Not in index |
| CyberBench (Vals AI)Coding | 69.5% | Not in index |
| Finance Agent (Vals AI)Agentic work | 60.6% | Not in index |
| Tax Agent Bench (Vals AI)Agentic work | 32.8% | 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 | 57.0% | Not in index |
| BioMysteryBench (Vals AI)Agentic work | 64.8% | 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 | 68.5% | Not in index |
| MysteryMechanism (Vals AI)Reasoning | Not measured | Not in index |
| MMMU Pro (Vals AI)Reasoning | 86.1% | 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 | 47.7% | Not in index |
| LegalBench (Vals AI)Knowledge | 85.3% | Not in index |
| CaseLaw (Vals AI)Knowledge | Not measured | Not in index |
| CorpFin (Vals AI)Knowledge | 70.9% | Not in index |
| TaxEval (Vals AI)Knowledge | 80.4% | Not in index |
| MortgageTax (Vals AI)Knowledge | 65.4% | Not in index |
| MedQA (Vals AI)Knowledge | Not measured | Not in index |
| MedCode (Vals AI)Knowledge | 49.4% | Not in index |
| MedScribe (Vals AI)General | 90.1% | Not in index |
| Vals Multimodal IndexGeneral | 69.8% | Not in index |
| AA Math IndexMath | Not measured | Not in index |
| GPQA Diamond (Artificial Analysis run)Reasoning | 90.4% | Not in index |
| Humanity's Last Exam (Artificial Analysis run)Reasoning | 45.5% | 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 | 57.4% | 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 | 79.0% | 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 | Not measured | Not in index |
| FrontierCodeCoding | Not measured | Not in index |
| FrontierSWECoding | 12.0% | Not in index |
| GSO-BenchCoding | Not measured | Not in index |
| WeirdMLCoding | 60.3% | Not in index |
| MirrorCodeCoding | Not measured | Not in index |
| APEX-AgentsAgentic work | 45.4% | 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 | Not measured | Not in index |
| BALROGAgentic work | Not measured | Not in index |
| DeepResearch BenchAgentic work | Not measured | Not in index |
| PostTrainBenchAgentic work | Not measured | Not in index |
| GPQA Diamond (Epoch AI run)Reasoning | Not measured | Not in index |
| ARC-AGIReasoning | Not measured | Not in index |
| ARC-AGI-2Reasoning | Not measured | Not in index |
| Humanity's Last ExamReasoning | Not measured | Not in index |
| SimpleBenchReasoning | 74.5% | Not in index |
| Chess puzzlesReasoning | 27.0% | Not in index |
| Mystery game puzzlesReasoning | Not measured | Not in index |
| EBR-benchReasoning | Not measured | Not in index |
| OTIS Mock AIMEMath | Not measured | Not in index |
| FrontierMath, tiers 1 to 3Math | Not measured | Not in index |
| FrontierMath, tier 4Math | Not measured | Not in index |
| ProofBenchMath | 43.0% | Not in index |
| MATH level 5Math | Not measured | Not in index |
| GSM8KMath | Not measured | Not in index |
| SimpleQA VerifiedKnowledge | 60.3% | Not in index |
| MMLUKnowledge | Not measured | Not in index |
| GeoBenchKnowledge | Not measured | Not in index |
| DTBenchGeneral | 94.7% | Not in index |
| LMCAGeneral | 48.4% | 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 | Not measured | 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 | Not measured | Not in index |
| Epoch Capabilities IndexIntelligence | 155.1 | Not in index |
| LMArena TextGeneral | 1482 | Not in index |
| LMArena Text: codingCoding | 1505 | Not in index |
| LMArena Text: hard promptsReasoning | 1489 | Not in index |
| LMArena Text: mathMath | 1484 | Not in index |
| LMArena Text: instruction followingGeneral | 1462 | Not in index |
| LMArena Text: creative writingGeneral | 1436 | Not in index |
| LMArena VisionGeneral | 1304 | Not in index |
| LMArena Text: EnglishGeneral | 1483 | Not in index |
| LMArena Text: non-EnglishGeneral | 1476 | Not in index |
| LMArena Text: ChineseGeneral | 1509 | Not in index |
| LMArena Text: GermanGeneral | Not measured | Not in index |
| LMArena Text: JapaneseGeneral | Not measured | Not in index |
| LMArena Text: KoreanGeneral | 1462 | Not in index |
| LMArena Text: FrenchGeneral | 1495 | Not in index |
| LMArena Text: SpanishGeneral | 1484 | Not in index |
| LMArena Text: RussianGeneral | 1483 | Not in index |
| LMArena Text: PolishGeneral | Not measured | Not in index |
| LMArena Text: multi-turnGeneral | 1502 | Not in index |
| LMArena Text: longer queriesGeneral | 1473 | Not in index |
| LMArena Text: expertReasoning | 1475 | Not in index |
| LMArena Text: hard prompts in EnglishReasoning | 1487 | Not in index |
| LMArena Text: software and ITCoding | 1505 | Not in index |
| LMArena Text: mathematical workMath | 1480 | Not in index |
| LMArena Text: scienceKnowledge | 1500 | Not in index |
| LMArena Text: medicine and healthcareKnowledge | 1496 | Not in index |
| LMArena Text: legal and governmentKnowledge | 1517 | Not in index |
| LMArena Text: business and financeKnowledge | 1484 | Not in index |
| LMArena Text: writing and languageGeneral | 1453 | Not in index |
| LMArena Text: entertainment and mediaGeneral | 1443 | Not in index |
| LMArena WebDev: ReactCoding | 1526 | Not in index |
| LMArena WebDev: HTMLCoding | 1543 | Not in index |
| LMArena WebDev: from an imageCoding | Not measured | Not in index |
| LMArena Vision: EnglishGeneral | 1291 | Not in index |
| LMArena Vision: ChineseGeneral | Not measured | Not in index |
| LMArena Vision: reading textGeneral | 1313 | Not in index |
| LMArena Vision: diagramsReasoning | 1317 | 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 | Not measured | 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 | 78.2% | $1.4657 per task | Output tokens per task 35,890 |
| LiveBench reasoning | 90.0% | $0.0994 per task | Output tokens per task 23,381 |
| LiveBench data analysis | 76.5% | $0.1094 per task | Output tokens per task 25,752 |
| LiveBench research | 67.7% | $1.7832 per task | Output tokens per task 28,067 |
| LiveBench browser | 36.0% | $2.4945 per task | Output tokens per task 36,088 |
| LiveBench long agentic | 21.3% | $3.9488 per task | Output tokens per task 122,638 |
| LiveBench design | 67.1% | $0.8562 per task | Output tokens per task 44,091 |
| SWE-bench Verified (Vals AI) | 86.6% | $0.55 per test | Duration, as printed 8m 07s |
| Terminal-Bench 4 (Vals AI) | 6.1% | $4.14 per test | Duration, as printed 1h 18m |
| Vibe Code Bench (Vals AI) | 79.1% | $1.53 per test | Duration, as printed 19m 55s |
| Code migration (Vals AI) | 29.9% | $3.78 per test | Duration, as printed 31m 07s |
| ProgramBench (Vals AI) | 0.5% | $2.47 per test | Duration, as printed 26m 38s |
| SREBench (Vals AI) | 0.0% | $23.43 per test | Duration, as printed 1h 40m |
|---|---|---|---|
| IOI (Vals AI) | 21.8% | $2.64 per test | Duration, as printed 25m 35s |
| Terminal-Bench 2.1 (Vals AI) | 69.7% | $0.50 per test | Duration, as printed 14m 39s |
| SkillsBench (Vals AI) | 53.0% | $0.65 per test | Duration, as printed 13m 00s |
| CyberBench (Vals AI) | 69.5% | $2.15 per test | Duration, as printed 20m 21s |
| Finance Agent (Vals AI) | 60.6% | $0.77 per test | Duration, as printed 5m 04s |
| Tax Agent Bench (Vals AI) | 32.8% | $0.27 per test | Duration, as printed 1m 60s |
| Legal Research Bench (Vals AI) | 43.8% | $0.51 per test | Duration, as printed 5m 07s |
| Excel Modeling Benchmark (Vals AI) | 57.0% | $2.31 per test | Duration, as printed 17m 07s |
| BioMysteryBench (Vals AI) | 64.8% | $0.99 per test | Duration, as printed 23m 37s |
| Public Benefits Bench (Vals AI) | 68.5% | $0.59 per test | Nothing else |
| Vals Multimodal Index | 69.8% | $0.51 per test | Duration, as printed 7m 26s |
| FrontierSWE | 12.0% | $27.81 average cost per task | Best of 5 runs 18.4% · Hours per task 4.6 h |
| WeirdML | 60.3% | $0.3801 per run | Median lines of code 272 |
| ProofBench | 43.0% | $0.442 per test | Time per proof 7m 49s |
| LMArena WebDev | 1534 Elo | Not published | Votes 2,163 · Interval (±) ±13.7 |
| MMLU Pro | 88.3% | Not published | Latency, as printed 44 s |
| Design Arena: websites | 1313 Elo | Not published | Battles 31,751 |
| Design Arena: UI components | 1300 Elo | Not published | Battles 1,917 |
| Design Arena: game dev | 1302 Elo | Not published | Battles 12,865 |
| Design Arena: data viz | 1334 Elo | Not published | Battles 1,726 |
| Design Arena: 3D | 1301 Elo | Not published | Battles 6,589 |
| Design Arena: all code categories | 1313 Elo | Not published | Battles 50,357 |
| Design Arena: SVG | 1285 Elo | Not published | Battles 2,084 |
| Design Arena: ASCII art | 1284 Elo | Not published | Battles 553 |
| Design Arena: agents building web apps | 1222 Elo | Not published | Battles 2,088 |
| Design Arena: agents building full-stack apps | 1210 Elo | Not published | Battles 1,907 |
| Design Arena: agents building mobile apps | 1182 Elo | Not published | Battles 1,294 |
| Design Arena: agents building Android apps | 1228 Elo | Not published | Battles 844 |
| Design Arena: agents building games | 1179 Elo | Not published | Battles 620 |
| Design Arena: HTML slides | 1135 Elo | Not published | Battles 2,091 |
| Design Arena: PowerPoint slides | 1198 Elo | Not published | Battles 1,755 |
| MMMU Pro (Vals AI) | 86.1% | Not published | Latency, as printed 1m 14s |
| SAGE (Vals AI) | 47.7% | Not published | Latency, as printed 29 s |
| LegalBench (Vals AI) | 85.3% | Not published | Latency, as printed 30 s |
| CorpFin (Vals AI) | 70.9% | Not published | Latency, as printed 30 s |
| TaxEval (Vals AI) | 80.4% | Not published | Latency, as printed 48 s |
| MortgageTax (Vals AI) | 65.4% | Not published | Latency, as printed 45 s |
| MedCode (Vals AI) | 49.4% | Not published | Latency, as printed 1m 00s |
| MedScribe (Vals AI) | 90.1% | Not published | Latency, as printed 1m 01s |
| APEX-Agents | 45.4% | Not published | Mean score 59.8% |
| LMArena Text | 1482 Elo | Not published | Votes 9,578 · Interval (±) ±6.8 |
| LMArena Text: coding | 1505 Elo | Not published | Votes 2,474 · Interval (±) ±12.3 |
| LMArena Text: hard prompts | 1489 Elo | Not published | Votes 6,116 · Interval (±) ±8.2 |
| LMArena Text: math | 1484 Elo | Not published | Votes 484 · Interval (±) ±26.1 |
| LMArena Text: instruction following | 1462 Elo | Not published | Votes 3,379 · Interval (±) ±10.6 |
| LMArena Text: creative writing | 1436 Elo | Not published | Votes 2,023 · Interval (±) ±14.1 |
| LMArena Vision | 1304 Elo | Not published | Votes 1,948 · Interval (±) ±14.3 |
| LMArena Text: English | 1483 Elo | Not published | Votes 3,794 · Interval (±) ±9.9 |
| LMArena Text: non-English | 1476 Elo | Not published | Votes 5,780 · Interval (±) ±8.5 |
| LMArena Text: Chinese | 1509 Elo | Not published | Votes 821 · Interval (±) ±21.1 |
| LMArena Text: Korean | 1462 Elo | Not published | Votes 196 · Interval (±) ±40.7 |
| LMArena Text: French | 1495 Elo | Not published | Votes 352 · Interval (±) ±32.9 |
| LMArena Text: Spanish | 1484 Elo | Not published | Votes 308 · Interval (±) ±32.4 |
| LMArena Text: Russian | 1483 Elo | Not published | Votes 1,205 · Interval (±) ±17.3 |
| LMArena Text: multi-turn | 1502 Elo | Not published | Votes 1,393 · Interval (±) ±16.5 |
| LMArena Text: longer queries | 1473 Elo | Not published | Votes 4,199 · Interval (±) ±9.8 |
| LMArena Text: expert | 1475 Elo | Not published | Votes 1,014 · Interval (±) ±18.4 |
| LMArena Text: hard prompts in English | 1487 Elo | Not published | Votes 2,442 · Interval (±) ±12.2 |
| LMArena Text: software and IT | 1505 Elo | Not published | Votes 3,594 · Interval (±) ±10.3 |
| LMArena Text: mathematical work | 1480 Elo | Not published | Votes 520 · Interval (±) ±25.9 |
| LMArena Text: science | 1500 Elo | Not published | Votes 1,537 · Interval (±) ±15.2 |
| LMArena Text: medicine and healthcare | 1496 Elo | Not published | Votes 660 · Interval (±) ±23.4 |
| LMArena Text: legal and government | 1517 Elo | Not published | Votes 757 · Interval (±) ±21.7 |
| LMArena Text: business and finance | 1484 Elo | Not published | Votes 1,717 · Interval (±) ±14.6 |
| LMArena Text: writing and language | 1453 Elo | Not published | Votes 2,677 · Interval (±) ±12.3 |
| LMArena Text: entertainment and media | 1443 Elo | Not published | Votes 2,452 · Interval (±) ±12.7 |
| LMArena WebDev: React | 1526 Elo | Not published | Votes 1,487 · Interval (±) ±16.5 |
| LMArena WebDev: HTML | 1543 Elo | Not published | Votes 244 · Interval (±) ±41.6 |
| LMArena Vision: English | 1291 Elo | Not published | Votes 695 · Interval (±) ±23.3 |
| LMArena Vision: reading text | 1313 Elo | Not published | Votes 1,343 · Interval (±) ±16.9 |
| LMArena Vision: diagrams | 1317 Elo | Not published | Votes 544 · Interval (±) ±26.1 |