As of October 20, 2026, OpenAI GPT-5.6 Luna ranks #37 of 213 models overall with 37.3 on the Artificial Analysis Intelligence Index. Its strongest category is reasoning, where it ranks #27 of 203. OpenAI GPT-5.6 Luna costs $0.20 per million input tokens and $1.20 per million output tokens. It was released on July 9, 2026.
Its output price ranks 147 of 349 priced models, counting from the cheapest.
GPT-5.6 Luna is a fast, cost-efficient model in OpenAI's GPT-5.6 series. It is suited for high-volume, latency-sensitive tasks such as chat, classification, and lightweight agentic workflows, providing capable reasoning for...
openai/gpt-5.6-luna 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, LiveCodeBench (Vals AI), SWE-bench Multimodal (Vals AI), LiveCodeBench (Artificial Analysis run), Terminal-Bench Hard (Artificial Analysis run), Terminal-Bench, FrontierSWE, GSO-Bench, MirrorCode, Cybench
Not measured on 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, Harvey's Legal Agent Benchmark (Vals AI), 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, DeepResearch Bench, PostTrainBench, TheAgentCompany, OSWorld, SpireClimb, LMArena Search
Not measured on Humanity's Last Exam, 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 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, 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 | 73.6% | 20% |
| LMArena WebDevCoding | 1518 | 15% |
| Vals IndexGeneral | Not measured | Not in index |
| GPQA DiamondReasoning | 91.7% | Not in index |
| AIMEMath | Not measured | Not in index |
| MMLU ProKnowledge | 86.0% | Not in index |
| AA Intelligence IndexIntelligence | 37.3 | Not in index |
| AA Coding IndexCoding | 71.4 | Not in index |
| AA Agentic IndexAgentic work | 42.1 | Not in index |
| Design Arena: websitesWeb design | 1256 | Not in index |
| Design Arena: UI componentsWeb design | 1252 | Not in index |
| Design Arena: game devWeb design | 1194 | Not in index |
| Design Arena: data vizWeb design | 1210 | Not in index |
| Design Arena: 3DWeb design | 1121 | Not in index |
| Design Arena: all code categoriesWeb design | 1231 | Not in index |
| Design Arena: SVGWeb design | 1194 | Not in index |
| Design Arena: ASCII artWeb design | 1144 | 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 | 85.6% | Not in index |
| LiveBench data analysisGeneral | 78.0% | Not in index |
| LiveBench researchAgentic work | 51.0% | Not in index |
| LiveBench browserAgentic work | 68.0% | Not in index |
| LiveBench long agenticAgentic work | 30.4% | Not in index |
| LiveBench designWeb design | 76.0% | Not in index |
| LiveCodeBench (Vals AI)Coding | Not measured | Not in index |
| SWE-bench Verified (Vals AI)Coding | 93.0% | Not in index |
| Terminal-Bench 4 (Vals AI)Coding | 11.6% | Not in index |
| Vibe Code Bench (Vals AI)Coding | 77.1% | Not in index |
| Code migration (Vals AI)Coding | 44.5% | Not in index |
| ProgramBench (Vals AI)Coding | 0.0% | Not in index |
| SREBench (Vals AI)Agentic work | 1.5% | Not in index |
| IOI (Vals AI)Coding | 61.8% | Not in index |
| Terminal-Bench 2.1 (Vals AI)Coding | 79.0% | Not in index |
| SWE-bench Multimodal (Vals AI)Coding | Not measured | Not in index |
| Vibe Code Bench 1-100 (Vals AI)Coding | 22.6% | Not in index |
| SkillsBench (Vals AI)Coding | 60.5% | Not in index |
| CyberBench (Vals AI)Coding | 73.6% | Not in index |
| Finance Agent (Vals AI)Agentic work | 55.0% | Not in index |
| Tax Agent Bench (Vals AI)Agentic work | 24.8% | Not in index |
| Legal Research Bench (Vals AI)Agentic work | 36.5% | Not in index |
| Harvey's Legal Agent Benchmark (Vals AI)Agentic work | Not measured | Not in index |
| Excel Modeling Benchmark (Vals AI)Agentic work | 67.1% | Not in index |
| BioMysteryBench (Vals AI)Agentic work | 61.5% | Not in index |
| Terminal-Bench-Science (Vals AI)Agentic work | 0.0% | Not in index |
| Vals Science IndexAgentic work | 25.3% | 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 | 61.2% | Not in index |
| MysteryMechanism (Vals AI)Reasoning | 14.4% | Not in index |
| MMMU Pro (Vals AI)Reasoning | 85.0% | 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 | 44.2% | Not in index |
| LegalBench (Vals AI)Knowledge | 84.0% | Not in index |
| CaseLaw (Vals AI)Knowledge | Not measured | Not in index |
| CorpFin (Vals AI)Knowledge | 64.2% | Not in index |
| TaxEval (Vals AI)Knowledge | 76.2% | Not in index |
| MortgageTax (Vals AI)Knowledge | 67.3% | Not in index |
| MedQA (Vals AI)Knowledge | Not measured | Not in index |
| MedCode (Vals AI)Knowledge | 42.4% | Not in index |
| MedScribe (Vals AI)General | 84.4% | Not in index |
| Vals Multimodal IndexGeneral | 69.1% | Not in index |
| AA Math IndexMath | Not measured | Not in index |
| GPQA Diamond (Artificial Analysis run)Reasoning | 91.1% | Not in index |
| Humanity's Last Exam (Artificial Analysis run)Reasoning | 39.5% | 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 | 53.6% | 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 | 83.7% | 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 | 67.2% | Not in index |
| FrontierCodeCoding | 39.8% | Not in index |
| FrontierSWECoding | Not measured | Not in index |
| GSO-BenchCoding | Not measured | Not in index |
| WeirdMLCoding | 60.9% | Not in index |
| MirrorCodeCoding | Not measured | Not in index |
| APEX-AgentsAgentic work | 43.0% | 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 | 45.6% | Not in index |
| DeepResearch BenchAgentic work | Not measured | Not in index |
| PostTrainBenchAgentic work | Not measured | Not in index |
| GPQA Diamond (Epoch AI run)Reasoning | 91.6% | Not in index |
| ARC-AGIReasoning | 88.0% | Not in index |
| ARC-AGI-2Reasoning | 59.5% | Not in index |
| Humanity's Last ExamReasoning | Not measured | Not in index |
| SimpleBenchReasoning | 46.8% | Not in index |
| Chess puzzlesReasoning | 43.0% | Not in index |
| Mystery game puzzlesReasoning | 21.0% | Not in index |
| EBR-benchReasoning | Not measured | Not in index |
| OTIS Mock AIMEMath | 98.3% | Not in index |
| FrontierMath, tiers 1 to 3Math | 82.1% | Not in index |
| FrontierMath, tier 4Math | 61.0% | Not in index |
| ProofBenchMath | 60.0% | Not in index |
| MATH level 5Math | Not measured | Not in index |
| GSM8KMath | Not measured | Not in index |
| SimpleQA VerifiedKnowledge | 41.0% | Not in index |
| MMLUKnowledge | Not measured | Not in index |
| GeoBenchKnowledge | Not measured | Not in index |
| DTBenchGeneral | 89.1% | Not in index |
| LMCAGeneral | 48.5% | 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 | 61.9% | 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 | 1667.4 | Not in index |
| Vending-Bench 2Agentic work | $4,095 | Not in index |
| Epoch Capabilities IndexIntelligence | 156.3 | Not in index |
| LMArena TextGeneral | 1431 | Not in index |
| LMArena Text: codingCoding | 1466 | Not in index |
| LMArena Text: hard promptsReasoning | 1451 | Not in index |
| LMArena Text: mathMath | 1459 | Not in index |
| LMArena Text: instruction followingGeneral | 1437 | Not in index |
| LMArena Text: creative writingGeneral | 1396 | Not in index |
| LMArena VisionGeneral | 1257 | Not in index |
| LMArena Text: EnglishGeneral | 1441 | Not in index |
| LMArena Text: non-EnglishGeneral | 1417 | Not in index |
| LMArena Text: ChineseGeneral | 1469 | Not in index |
| LMArena Text: GermanGeneral | 1455 | Not in index |
| LMArena Text: JapaneseGeneral | 1414 | Not in index |
| LMArena Text: KoreanGeneral | 1416 | Not in index |
| LMArena Text: FrenchGeneral | 1458 | Not in index |
| LMArena Text: SpanishGeneral | 1446 | Not in index |
| LMArena Text: RussianGeneral | 1428 | Not in index |
| LMArena Text: PolishGeneral | 1404 | Not in index |
| LMArena Text: multi-turnGeneral | 1434 | Not in index |
| LMArena Text: longer queriesGeneral | 1437 | Not in index |
| LMArena Text: expertReasoning | 1478 | Not in index |
| LMArena Text: hard prompts in EnglishReasoning | 1460 | Not in index |
| LMArena Text: software and ITCoding | 1463 | Not in index |
| LMArena Text: mathematical workMath | 1470 | Not in index |
| LMArena Text: scienceKnowledge | 1433 | Not in index |
| LMArena Text: medicine and healthcareKnowledge | 1399 | Not in index |
| LMArena Text: legal and governmentKnowledge | 1446 | Not in index |
| LMArena Text: business and financeKnowledge | 1438 | Not in index |
| LMArena Text: writing and languageGeneral | 1419 | Not in index |
| LMArena Text: entertainment and mediaGeneral | 1402 | Not in index |
| LMArena WebDev: ReactCoding | 1508 | Not in index |
| LMArena WebDev: HTMLCoding | 1520 | Not in index |
| LMArena WebDev: from an imageCoding | 1517 | Not in index |
| LMArena Vision: EnglishGeneral | 1263 | Not in index |
| LMArena Vision: ChineseGeneral | 1294 | Not in index |
| LMArena Vision: reading textGeneral | 1264 | Not in index |
| LMArena Vision: diagramsReasoning | 1273 | Not in index |
| LMArena Vision: homeworkReasoning | 1282 | Not in index |
| LMArena Vision: humorGeneral | 1190 | Not in index |
| LMArena Vision: captioningGeneral | Not measured | Not in index |
| LMArena Vision: recognizing thingsGeneral | Not measured | Not in index |
| LMArena Vision: creative writingGeneral | 1257 | Not in index |
| LMArena SearchAgentic work | Not measured | Not in index |
| LMArena DocumentGeneral | 1457 | 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 | 73.6% | $1.8232 per task | Output tokens per task 35,428 |
| LiveBench reasoning | 85.6% | $0.0277 per task | Output tokens per task 22,753 |
| LiveBench data analysis | 78.0% | $0.0267 per task | Output tokens per task 21,599 |
| LiveBench research | 51.0% | $0.8208 per task | Output tokens per task 69,492 |
| LiveBench browser | 68.0% | $0.0973 per task | Output tokens per task 10,159 |
| LiveBench long agentic | 30.4% | $1.1012 per task | Output tokens per task 234,057 |
| LiveBench design | 76.0% | $0.0895 per task | Output tokens per task 27,152 |
| SWE-bench Verified (Vals AI) | 93.0% | $0.04 per test | Duration, as printed 3m 21s |
| Terminal-Bench 4 (Vals AI) | 11.6% | $0.73 per test | Duration, as printed 35m 55s |
| Vibe Code Bench (Vals AI) | 77.1% | $0.73 per test | Duration, as printed 25m 52s |
| Code migration (Vals AI) | 44.5% | $1.88 per test | Duration, as printed 58m 35s |
| ProgramBench (Vals AI) | 0.0% | $0.94 per test | Duration, as printed 41m 34s |
| SREBench (Vals AI) | 1.5% | $3.44 per test | Duration, as printed 1h 42m |
|---|---|---|---|
| IOI (Vals AI) | 61.8% | $0.58 per test | Duration, as printed 1h 10m |
| Terminal-Bench 2.1 (Vals AI) | 79.0% | $0.05 per test | Duration, as printed 5m 56s |
| Vibe Code Bench 1-100 (Vals AI) | 22.6% | $4.91 per test | Duration, as printed 2h 03m |
| SkillsBench (Vals AI) | 60.5% | $0.21 per test | Duration, as printed 5m 20s |
| CyberBench (Vals AI) | 73.6% | $0.40 per test | Duration, as printed 16m 15s |
| Finance Agent (Vals AI) | 55.0% | $0.28 per test | Duration, as printed 12m 52s |
| Tax Agent Bench (Vals AI) | 24.8% | $0.47 per test | Duration, as printed 42m 46s |
| Legal Research Bench (Vals AI) | 36.5% | $0.85 per test | Duration, as printed 39m 34s |
| Excel Modeling Benchmark (Vals AI) | 67.1% | $0.37 per test | Duration, as printed 11m 00s |
| BioMysteryBench (Vals AI) | 61.5% | $0.09 per test | Duration, as printed 18m 31s |
| Terminal-Bench-Science (Vals AI) | 0.0% | $0.58 per test | Duration, as printed 2h 03m |
| Vals Science Index | 25.3% | $0.26 per test | Duration, as printed 50m 00s |
| Public Benefits Bench (Vals AI) | 61.2% | $0.27 per test | Nothing else |
| MysteryMechanism (Vals AI) | 14.4% | $0.11 per test | Duration, as printed 8m 13s |
| Vals Multimodal Index | 69.1% | $0.16 per test | Duration, as printed 6m 47s |
| DeepSWE | 67.2% | $3.0281 mean cost per task | Solved in 4 tries 90.3% · Output tokens per task 73,400 · Agent steps per task 102 |
| WeirdML | 60.9% | $0.20 per run | Median lines of code 289 |
| ARC-AGI | 88.0% | $0.32 per task | Nothing else |
| ARC-AGI-2 | 59.5% | $0.67 per task | Nothing else |
| ProofBench | 60.0% | $0.1233 per test | Time per proof 8m 34s |
| Surface Evolver Bench | 61.9% | $1.0079 of the run | Pass rate 18.8% · Tokens for the run 1.2M |
| ALE-Bench | 1667.4 | $0.3592 per problem | Tokens per problem 85,180 |
| LMArena WebDev | 1518 Elo | Not published | Votes 12,501 · Interval (±) ±6.4 |
| GPQA Diamond | 91.7% | Not published | Latency, as printed 54 s |
| MMLU Pro | 86.0% | Not published | Latency, as printed 17 s |
| Design Arena: websites | 1256 Elo | Not published | Battles 13,154 |
| Design Arena: UI components | 1252 Elo | Not published | Battles 1,809 |
| Design Arena: game dev | 1194 Elo | Not published | Battles 3,856 |
| Design Arena: data viz | 1210 Elo | Not published | Battles 1,032 |
| Design Arena: 3D | 1121 Elo | Not published | Battles 3,772 |
| Design Arena: all code categories | 1231 Elo | Not published | Battles 21,673 |
| Design Arena: SVG | 1194 Elo | Not published | Battles 1,549 |
| Design Arena: ASCII art | 1144 Elo | Not published | Battles 316 |
| MMMU Pro (Vals AI) | 85.0% | Not published | Latency, as printed 35 s |
| SAGE (Vals AI) | 44.2% | Not published | Latency, as printed 52 s |
| LegalBench (Vals AI) | 84.0% | Not published | Latency, as printed 5.9 s |
| CorpFin (Vals AI) | 64.2% | Not published | Latency, as printed 17 s |
| TaxEval (Vals AI) | 76.2% | Not published | Latency, as printed 1m 17s |
| MortgageTax (Vals AI) | 67.3% | Not published | Latency, as printed 23 s |
| MedCode (Vals AI) | 42.4% | Not published | Latency, as printed 1m 21s |
| MedScribe (Vals AI) | 84.4% | Not published | Latency, as printed 1m 57s |
| APEX-Agents | 43.0% | Not published | Mean score 57.8% |
| LMArena Text | 1431 Elo | Not published | Votes 41,109 · Interval (±) ±4.3 |
| LMArena Text: coding | 1466 Elo | Not published | Votes 11,127 · Interval (±) ±6.6 |
| LMArena Text: hard prompts | 1451 Elo | Not published | Votes 27,008 · Interval (±) ±5.0 |
| LMArena Text: math | 1459 Elo | Not published | Votes 1,927 · Interval (±) ±13.7 |
| LMArena Text: instruction following | 1437 Elo | Not published | Votes 14,621 · Interval (±) ±6.1 |
| LMArena Text: creative writing | 1396 Elo | Not published | Votes 8,603 · Interval (±) ±7.5 |
| LMArena Vision | 1257 Elo | Not published | Votes 11,055 · Interval (±) ±7.4 |
| LMArena Text: English | 1441 Elo | Not published | Votes 16,656 · Interval (±) ±5.7 |
| LMArena Text: non-English | 1417 Elo | Not published | Votes 24,449 · Interval (±) ±5.1 |
| LMArena Text: Chinese | 1469 Elo | Not published | Votes 3,218 · Interval (±) ±11.1 |
| LMArena Text: German | 1455 Elo | Not published | Votes 707 · Interval (±) ±23.0 |
| LMArena Text: Japanese | 1414 Elo | Not published | Votes 644 · Interval (±) ±25.5 |
| LMArena Text: Korean | 1416 Elo | Not published | Votes 788 · Interval (±) ±21.5 |
| LMArena Text: French | 1458 Elo | Not published | Votes 1,348 · Interval (±) ±17.4 |
| LMArena Text: Spanish | 1446 Elo | Not published | Votes 1,196 · Interval (±) ±17.7 |
| LMArena Text: Russian | 1428 Elo | Not published | Votes 4,732 · Interval (±) ±9.1 |
| LMArena Text: Polish | 1404 Elo | Not published | Votes 610 · Interval (±) ±24.0 |
| LMArena Text: multi-turn | 1434 Elo | Not published | Votes 6,622 · Interval (±) ±8.0 |
| LMArena Text: longer queries | 1437 Elo | Not published | Votes 19,367 · Interval (±) ±5.7 |
| LMArena Text: expert | 1478 Elo | Not published | Votes 4,671 · Interval (±) ±9.2 |
| LMArena Text: hard prompts in English | 1460 Elo | Not published | Votes 10,955 · Interval (±) ±6.6 |
| LMArena Text: software and IT | 1463 Elo | Not published | Votes 15,935 · Interval (±) ±5.8 |
| LMArena Text: mathematical work | 1470 Elo | Not published | Votes 2,323 · Interval (±) ±12.8 |
| LMArena Text: science | 1433 Elo | Not published | Votes 6,720 · Interval (±) ±7.9 |
| LMArena Text: medicine and healthcare | 1399 Elo | Not published | Votes 3,041 · Interval (±) ±11.5 |
| LMArena Text: legal and government | 1446 Elo | Not published | Votes 3,477 · Interval (±) ±10.7 |
| LMArena Text: business and finance | 1438 Elo | Not published | Votes 7,707 · Interval (±) ±7.5 |
| LMArena Text: writing and language | 1419 Elo | Not published | Votes 11,298 · Interval (±) ±6.7 |
| LMArena Text: entertainment and media | 1402 Elo | Not published | Votes 10,794 · Interval (±) ±6.9 |
| LMArena WebDev: React | 1508 Elo | Not published | Votes 7,697 · Interval (±) ±7.8 |
| LMArena WebDev: HTML | 1520 Elo | Not published | Votes 1,799 · Interval (±) ±15.4 |
| LMArena WebDev: from an image | 1517 Elo | Not published | Votes 4,324 · Interval (±) ±9.8 |
| LMArena Vision: English | 1263 Elo | Not published | Votes 3,794 · Interval (±) ±10.9 |
| LMArena Vision: Chinese | 1294 Elo | Not published | Votes 631 · Interval (±) ±24.9 |
| LMArena Vision: reading text | 1264 Elo | Not published | Votes 7,472 · Interval (±) ±7.9 |
| LMArena Vision: diagrams | 1273 Elo | Not published | Votes 2,789 · Interval (±) ±11.7 |
| LMArena Vision: homework | 1282 Elo | Not published | Votes 1,128 · Interval (±) ±18.2 |
| LMArena Vision: humor | 1190 Elo | Not published | Votes 502 · Interval (±) ±27.4 |
| LMArena Vision: creative writing | 1257 Elo | Not published | Votes 977 · Interval (±) ±19.9 |
| LMArena Document | 1457 Elo | Not published | Votes 5,766 · Interval (±) ±8.2 |