As of October 20, 2026, SpaceXAI Grok 4.7 ranks #12 of 213 models overall with 46.4 on the Artificial Analysis Intelligence Index. Its strongest category is reasoning, where it ranks #22 of 203. SpaceXAI Grok 4.7 costs $2.00 per million input tokens and $6.00 per million output tokens. It was released on September 21, 2026.
Its output price ranks 260 of 349 priced models, counting from the cheapest.
Listed on OpenRouter September 21, 2026, 29 days before our data. Results so far on 99 of 190 public boards; this page updates every day as boards publish.
Grok 4.7 is SpaceXAI's flagship model for coding, agentic tasks, and knowledge work, succeeding Grok 4.6. It is particularly strong at long-running software engineering tasks, verifying its own work, and...
x-ai/grok-4.7 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 4 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, AA Coding Index, LiveCodeBench (Vals AI), SWE-bench Verified (Vals AI), Vibe Code Bench 1-100 (Vals AI), SkillsBench (Vals AI), LiveCodeBench (Artificial Analysis run), Terminal-Bench Hard (Artificial Analysis run), Terminal-Bench, DeepSWE, GSO-Bench, WeirdML, MirrorCode, Cybench, ALE-Bench
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, Time Horizon Index (Vals AI), CUA-bench (Vals AI), τ²-Bench Telecom, METR time horizons, Remote Labor Index, GDPval, OSWorld 2.0, BALROG, DeepResearch Bench, PostTrainBench, TheAgentCompany, OSWorld, SpireClimb, LMArena Search
Not measured on GPQA Diamond, MMMU Pro (Vals AI), GPQA Diamond (Artificial Analysis run), Humanity's Last Exam, SimpleBench, EBR-bench, 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 MMLU Pro, CaseLaw (Vals AI), CorpFin (Vals AI), TaxEval (Vals AI), MortgageTax (Vals AI), MedQA (Vals AI), MMLU Pro (Artificial Analysis run), MMLU, GeoBench, AI2 Reasoning Challenge
Not measured on Design Arena: SVG, Design Arena: ASCII art
Not measured on Vals Multimodal Index, IFBench, Fiction.LiveBench, Creative writing (Lech Mazur), CL-bench, Surface Evolver Bench, ExploitBench, HellaSwag, WinoGrande, PIQA, CL-bench Life, LMArena Vision: humor, LMArena Vision: captioning, LMArena Vision: recognizing things, 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 | 84.5% | 20% |
| LMArena WebDevCoding | 1637 | 15% |
| Vals IndexGeneral | 58.6% | Not in index |
| GPQA DiamondReasoning | Not measured | Not in index |
| AIMEMath | Not measured | Not in index |
| MMLU ProKnowledge | Not measured | Not in index |
| AA Intelligence IndexIntelligence | 46.4 | Not in index |
| AA Coding IndexCoding | Not measured | Not in index |
| AA Agentic IndexAgentic work | Not measured | Not in index |
| Design Arena: websitesWeb design | 1253 | Not in index |
| Design Arena: UI componentsWeb design | 1268 | Not in index |
| Design Arena: game devWeb design | 1313 | Not in index |
| Design Arena: data vizWeb design | 1226 | Not in index |
| Design Arena: 3DWeb design | 1267 | Not in index |
| Design Arena: all code categoriesWeb design | 1270 | Not in index |
| Design Arena: SVGWeb design | Not measured | 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 | 82.7% | Not in index |
| LiveBench data analysisGeneral | 76.9% | Not in index |
| LiveBench researchAgentic work | 86.4% | Not in index |
| LiveBench browserAgentic work | 60.0% | Not in index |
| LiveBench long agenticAgentic work | 50.1% | Not in index |
| LiveBench designWeb design | 78.0% | Not in index |
| LiveCodeBench (Vals AI)Coding | Not measured | Not in index |
| SWE-bench Verified (Vals AI)Coding | Not measured | Not in index |
| Terminal-Bench 4 (Vals AI)Coding | 28.8% | Not in index |
| Vibe Code Bench (Vals AI)Coding | 86.2% | Not in index |
| Code migration (Vals AI)Coding | 44.8% | Not in index |
| ProgramBench (Vals AI)Coding | 0.5% | Not in index |
| SREBench (Vals AI)Agentic work | 3.8% | Not in index |
| IOI (Vals AI)Coding | 57.7% | Not in index |
| Terminal-Bench 2.1 (Vals AI)Coding | 73.4% | Not in index |
| SWE-bench Multimodal (Vals AI)Coding | 42.9% | 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 | 69.5% | Not in index |
| Finance Agent (Vals AI)Agentic work | 52.3% | Not in index |
| Tax Agent Bench (Vals AI)Agentic work | 34.2% | Not in index |
| Legal Research Bench (Vals AI)Agentic work | 47.1% | Not in index |
| Harvey's Legal Agent Benchmark (Vals AI)Agentic work | 18.3% | Not in index |
| Excel Modeling Benchmark (Vals AI)Agentic work | 67.0% | Not in index |
| BioMysteryBench (Vals AI)Agentic work | 69.3% | Not in index |
| Terminal-Bench-Science (Vals AI)Agentic work | 10.0% | Not in index |
| Vals Science IndexAgentic work | 34.8% | 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 | 0.2% | Not in index |
| Public Benefits Bench (Vals AI)General | 65.6% | Not in index |
| MysteryMechanism (Vals AI)Reasoning | 25.2% | Not in index |
| MMMU Pro (Vals AI)Reasoning | Not measured | 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 | 40.8% | Not in index |
| LegalBench (Vals AI)Knowledge | 84.4% | Not in index |
| CaseLaw (Vals AI)Knowledge | Not measured | Not in index |
| CorpFin (Vals AI)Knowledge | Not measured | Not in index |
| TaxEval (Vals AI)Knowledge | Not measured | Not in index |
| MortgageTax (Vals AI)Knowledge | Not measured | Not in index |
| MedQA (Vals AI)Knowledge | Not measured | Not in index |
| MedCode (Vals AI)Knowledge | 49.5% | Not in index |
| MedScribe (Vals AI)General | 89.4% | 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 | 43.1% | 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 | 57.8% | 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 | 80.0% | 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 | 47.6% | Not in index |
| FrontierSWECoding | 29.5% | Not in index |
| GSO-BenchCoding | Not measured | Not in index |
| WeirdMLCoding | Not measured | Not in index |
| MirrorCodeCoding | Not measured | Not in index |
| APEX-AgentsAgentic work | 54.6% | 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 | 92.7% | Not in index |
| ARC-AGIReasoning | 90.2% | Not in index |
| ARC-AGI-2Reasoning | 61.4% | Not in index |
| Humanity's Last ExamReasoning | Not measured | Not in index |
| SimpleBenchReasoning | Not measured | Not in index |
| Chess puzzlesReasoning | 41.0% | Not in index |
| Mystery game puzzlesReasoning | 29.0% | Not in index |
| EBR-benchReasoning | Not measured | Not in index |
| OTIS Mock AIMEMath | 98.1% | Not in index |
| FrontierMath, tiers 1 to 3Math | 53.0% | Not in index |
| FrontierMath, tier 4Math | 17.1% | Not in index |
| ProofBenchMath | 26.0% | Not in index |
| MATH level 5Math | Not measured | Not in index |
| GSM8KMath | Not measured | Not in index |
| SimpleQA VerifiedKnowledge | 56.0% | Not in index |
| MMLUKnowledge | Not measured | Not in index |
| GeoBenchKnowledge | Not measured | Not in index |
| DTBenchGeneral | 96.0% | Not in index |
| LMCAGeneral | 49.4% | 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 | 20.8% | 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 | Not measured | Not in index |
| Vending-Bench 2Agentic work | $10,537 | Not in index |
| Epoch Capabilities IndexIntelligence | 154.4 | Not in index |
| LMArena TextGeneral | 1401 | Not in index |
| LMArena Text: codingCoding | 1432 | Not in index |
| LMArena Text: hard promptsReasoning | 1415 | Not in index |
| LMArena Text: mathMath | 1412 | Not in index |
| LMArena Text: instruction followingGeneral | 1408 | Not in index |
| LMArena Text: creative writingGeneral | 1387 | Not in index |
| LMArena VisionGeneral | 1231 | Not in index |
| LMArena Text: EnglishGeneral | 1412 | Not in index |
| LMArena Text: non-EnglishGeneral | 1386 | Not in index |
| LMArena Text: ChineseGeneral | 1453 | Not in index |
| LMArena Text: GermanGeneral | 1353 | Not in index |
| LMArena Text: JapaneseGeneral | 1355 | Not in index |
| LMArena Text: KoreanGeneral | 1385 | Not in index |
| LMArena Text: FrenchGeneral | 1443 | Not in index |
| LMArena Text: SpanishGeneral | 1405 | Not in index |
| LMArena Text: RussianGeneral | 1400 | Not in index |
| LMArena Text: PolishGeneral | 1411 | Not in index |
| LMArena Text: multi-turnGeneral | 1391 | Not in index |
| LMArena Text: longer queriesGeneral | 1416 | Not in index |
| LMArena Text: expertReasoning | 1437 | Not in index |
| LMArena Text: hard prompts in EnglishReasoning | 1427 | Not in index |
| LMArena Text: software and ITCoding | 1423 | Not in index |
| LMArena Text: mathematical workMath | 1437 | Not in index |
| LMArena Text: scienceKnowledge | 1417 | Not in index |
| LMArena Text: medicine and healthcareKnowledge | 1399 | Not in index |
| LMArena Text: legal and governmentKnowledge | 1425 | Not in index |
| LMArena Text: business and financeKnowledge | 1389 | Not in index |
| LMArena Text: writing and languageGeneral | 1395 | Not in index |
| LMArena Text: entertainment and mediaGeneral | 1380 | Not in index |
| LMArena WebDev: ReactCoding | 1663 | Not in index |
| LMArena WebDev: HTMLCoding | 1627 | Not in index |
| LMArena WebDev: from an imageCoding | 1586 | Not in index |
| LMArena Vision: EnglishGeneral | 1229 | Not in index |
| LMArena Vision: ChineseGeneral | 1250 | Not in index |
| LMArena Vision: reading textGeneral | 1241 | Not in index |
| LMArena Vision: diagramsReasoning | 1254 | Not in index |
| LMArena Vision: homeworkReasoning | 1309 | 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 | 1217 | 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.
Neither board that publishes what a SWE-bench Verified attempt costs, Vals AI and swebench.com, has run this model. We leave the number out rather than estimate it.
LiveBench, on its own coding tasks, publishes what one task cost this model: $4.88, at a score of 84.5%. LiveBench counts that as $5.775 per successful task. Different tasks from SWE-bench, so it is not our number and does not enter its ranking. LiveBench coding
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 | 84.5% | $4.8799 per task | Output tokens per task 59,183 |
| Vals Index | 58.6% | $11.63 per test | Duration, as printed 33m 34s |
| LiveBench reasoning | 82.7% | $0.3851 per task | Output tokens per task 63,769 |
| LiveBench data analysis | 76.9% | $0.488 per task | Output tokens per task 80,144 |
| LiveBench research | 86.4% | $4.5773 per task | Output tokens per task 76,863 |
| LiveBench browser | 60.0% | $4.7778 per task | Output tokens per task 36,667 |
| LiveBench long agentic | 50.1% | $18.9333 per task | Output tokens per task 283,495 |
| LiveBench design | 78.0% | $3.3696 per task | Output tokens per task 117,654 |
| Terminal-Bench 4 (Vals AI) | 28.8% | $18.01 per test | Duration, as printed 50m 08s |
| Vibe Code Bench (Vals AI) | 86.2% | $15.83 per test | Duration, as printed 35m 47s |
| Code migration (Vals AI) | 44.8% | $36.55 per test | Duration, as printed 1h 09m |
| ProgramBench (Vals AI) | 0.5% | $46.49 per test | Duration, as printed 3h 38m |
| SREBench (Vals AI) | 3.8% | $64.77 per test | Duration, as printed 1h 41m |
|---|---|---|---|
| IOI (Vals AI) | 57.7% | $12.71 per test | Duration, as printed 46m 48s |
| Terminal-Bench 2.1 (Vals AI) | 73.4% | $1.08 per test | Duration, as printed 13m 18s |
| SWE-bench Multimodal (Vals AI) | 42.9% | $4.66 per test | Duration, as printed 21m 01s |
| CyberBench (Vals AI) | 69.5% | $8.54 per test | Duration, as printed 15m 30s |
| Finance Agent (Vals AI) | 52.3% | $2.72 per test | Duration, as printed 15m 33s |
| Tax Agent Bench (Vals AI) | 34.2% | $1.80 per test | Duration, as printed 16m 36s |
| Legal Research Bench (Vals AI) | 47.1% | $4.92 per test | Duration, as printed 21m 14s |
| Harvey's Legal Agent Benchmark (Vals AI) | 18.3% | $10.75 per test | Duration, as printed 35m 48s |
| Excel Modeling Benchmark (Vals AI) | 67.0% | $6.48 per test | Duration, as printed 34m 57s |
| BioMysteryBench (Vals AI) | 69.3% | $2.49 per test | Duration, as printed 11m 37s |
| Terminal-Bench-Science (Vals AI) | 10.0% | $17.04 per test | Duration, as printed 1h 33m |
| Vals Science Index | 34.8% | $7.12 per test | Duration, as printed 40m 34s |
| Public Benefits Bench (Vals AI) | 65.6% | $2.25 per test | Nothing else |
| MysteryMechanism (Vals AI) | 25.2% | $1.84 per test | Duration, as printed 17m 33s |
| FrontierSWE | 29.5% | $318.77 average cost per task | Best of 5 runs 41.1% · Hours per task 12.1 h |
| ProofBench | 26.0% | $0.788 per test | Time per proof 12m 47s |
| LMArena WebDev | 1637 Elo | Not published | Votes 5,303 · Interval (±) ±9.5 |
| Design Arena: websites | 1253 Elo | Not published | Battles 1,532 |
| Design Arena: UI components | 1268 Elo | Not published | Battles 291 |
| Design Arena: game dev | 1313 Elo | Not published | Battles 687 |
| Design Arena: data viz | 1226 Elo | Not published | Battles 135 |
| Design Arena: 3D | 1267 Elo | Not published | Battles 320 |
| Design Arena: all code categories | 1270 Elo | Not published | Battles 2,792 |
| SAGE (Vals AI) | 40.8% | Not published | Latency, as printed 4m 51s |
| LegalBench (Vals AI) | 84.4% | Not published | Latency, as printed 26 s |
| MedCode (Vals AI) | 49.5% | Not published | Latency, as printed 3m 33s |
| MedScribe (Vals AI) | 89.4% | Not published | Latency, as printed 2m 33s |
| APEX-Agents | 54.6% | Not published | Mean score 68.7% |
| LMArena Text | 1401 Elo | Not published | Votes 11,591 · Interval (±) ±6.4 |
| LMArena Text: coding | 1432 Elo | Not published | Votes 2,522 · Interval (±) ±12.1 |
| LMArena Text: hard prompts | 1415 Elo | Not published | Votes 7,054 · Interval (±) ±7.8 |
| LMArena Text: math | 1412 Elo | Not published | Votes 590 · Interval (±) ±23.4 |
| LMArena Text: instruction following | 1408 Elo | Not published | Votes 3,853 · Interval (±) ±10.1 |
| LMArena Text: creative writing | 1387 Elo | Not published | Votes 2,589 · Interval (±) ±12.5 |
| LMArena Vision | 1231 Elo | Not published | Votes 3,736 · Interval (±) ±10.6 |
| LMArena Text: English | 1412 Elo | Not published | Votes 4,571 · Interval (±) ±9.3 |
| LMArena Text: non-English | 1386 Elo | Not published | Votes 6,985 · Interval (±) ±7.7 |
| LMArena Text: Chinese | 1453 Elo | Not published | Votes 927 · Interval (±) ±19.5 |
| LMArena Text: German | 1353 Elo | Not published | Votes 179 · Interval (±) ±43.5 |
| LMArena Text: Japanese | 1355 Elo | Not published | Votes 225 · Interval (±) ±42.3 |
| LMArena Text: Korean | 1385 Elo | Not published | Votes 190 · Interval (±) ±43.1 |
| LMArena Text: French | 1443 Elo | Not published | Votes 385 · Interval (±) ±30.9 |
| LMArena Text: Spanish | 1405 Elo | Not published | Votes 422 · Interval (±) ±28.4 |
| LMArena Text: Russian | 1400 Elo | Not published | Votes 1,552 · Interval (±) ±14.9 |
| LMArena Text: Polish | 1411 Elo | Not published | Votes 164 · Interval (±) ±43.2 |
| LMArena Text: multi-turn | 1391 Elo | Not published | Votes 1,721 · Interval (±) ±14.6 |
| LMArena Text: longer queries | 1416 Elo | Not published | Votes 4,785 · Interval (±) ±9.3 |
| LMArena Text: expert | 1437 Elo | Not published | Votes 1,115 · Interval (±) ±17.6 |
| LMArena Text: hard prompts in English | 1427 Elo | Not published | Votes 2,803 · Interval (±) ±11.6 |
| LMArena Text: software and IT | 1423 Elo | Not published | Votes 4,071 · Interval (±) ±9.7 |
| LMArena Text: mathematical work | 1437 Elo | Not published | Votes 660 · Interval (±) ±21.8 |
| LMArena Text: science | 1417 Elo | Not published | Votes 1,982 · Interval (±) ±13.4 |
| LMArena Text: medicine and healthcare | 1399 Elo | Not published | Votes 814 · Interval (±) ±20.9 |
| LMArena Text: legal and government | 1425 Elo | Not published | Votes 1,016 · Interval (±) ±18.5 |
| LMArena Text: business and finance | 1389 Elo | Not published | Votes 1,996 · Interval (±) ±13.6 |
| LMArena Text: writing and language | 1395 Elo | Not published | Votes 3,233 · Interval (±) ±11.2 |
| LMArena Text: entertainment and media | 1380 Elo | Not published | Votes 2,948 · Interval (±) ±11.7 |
| LMArena WebDev: React | 1663 Elo | Not published | Votes 3,212 · Interval (±) ±12.0 |
| LMArena WebDev: HTML | 1627 Elo | Not published | Votes 855 · Interval (±) ±22.8 |
| LMArena WebDev: from an image | 1586 Elo | Not published | Votes 1,191 · Interval (±) ±17.4 |
| LMArena Vision: English | 1229 Elo | Not published | Votes 1,292 · Interval (±) ±17.6 |
| LMArena Vision: Chinese | 1250 Elo | Not published | Votes 182 · Interval (±) ±45.0 |
| LMArena Vision: reading text | 1241 Elo | Not published | Votes 2,508 · Interval (±) ±12.3 |
| LMArena Vision: diagrams | 1254 Elo | Not published | Votes 938 · Interval (±) ±19.8 |
| LMArena Vision: homework | 1309 Elo | Not published | Votes 517 · Interval (±) ±25.4 |
| LMArena Vision: creative writing | 1217 Elo | Not published | Votes 370 · Interval (±) ±32.5 |