As of October 20, 2026, Google Gemini 3.1 Pro Preview ranks #51 of 213 models overall with 29.7 on the Artificial Analysis Intelligence Index. Its strongest category is reasoning, where it ranks #4 of 203. Google Gemini 3.1 Pro Preview costs $2.00 per million input tokens and $12.00 per million output tokens. It was released on February 19, 2026.
Its output price ranks 303 of 349 priced models, counting from the cheapest.
Gemini 3.1 Pro Preview is Google’s frontier reasoning model, delivering enhanced software engineering performance, improved agentic reliability, and more efficient token usage across complex workflows. Building on the multimodal foundation...
google/gemini-3.1-pro-preview 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, SWE-bench Multimodal (Vals AI), SkillsBench (Vals AI), CyberBench (Vals AI), LiveCodeBench (Artificial Analysis run), FrontierCode, FrontierSWE, Cybench
Not measured on Epoch Capabilities Index
Not measured on Design Arena: spreadsheets, LiveBench research, LiveBench browser, LiveBench long agentic, Harvey's Legal Agent Benchmark (Vals AI), Time Horizon Index (Vals AI), CUA-bench (Vals AI), Robo-bench (Vals AI), Remote Labor Index, GDPval, OSWorld 2.0, TheAgentCompany, OSWorld, SpireClimb, LMArena Search
Not measured on LiveBench reasoning, VPCT, BIG-Bench Hard
Not measured on MATH 500 (Vals AI), MGSM (Vals AI), AA Math Index, AIME 2025 (Artificial Analysis run), MATH level 5, GSM8K
Not measured on MMLU Pro (Artificial Analysis run), MMLU, GeoBench, AI2 Reasoning Challenge
Not measured on LiveBench design
Not measured on Vals Index, LiveBench data analysis, Fiction.LiveBench, Creative writing (Lech Mazur), Surface Evolver Bench, HellaSwag, WinoGrande, PIQA
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 | Not measured | 20% |
| LMArena WebDevCoding | 1447 | 15% |
| Vals IndexGeneral | Not measured | Not in index |
| GPQA DiamondReasoning | 95.5% | Not in index |
| AIMEMath | 98.1% | Not in index |
| MMLU ProKnowledge | 91.0% | Not in index |
| AA Intelligence IndexIntelligence | 29.7 | Not in index |
| AA Coding IndexCoding | 68.8 | Not in index |
| AA Agentic IndexAgentic work | 8.2 | Not in index |
| Design Arena: websitesWeb design | 1234 | Not in index |
| Design Arena: UI componentsWeb design | 1227 | Not in index |
| Design Arena: game devWeb design | 1202 | Not in index |
| Design Arena: data vizWeb design | 1209 | Not in index |
| Design Arena: 3DWeb design | 1234 | Not in index |
| Design Arena: all code categoriesWeb design | 1231 | Not in index |
| Design Arena: SVGWeb design | 1284 | Not in index |
| Design Arena: ASCII artWeb design | 1270 | Not in index |
| Design Arena: agents building web appsAgentic work | 1126 | Not in index |
| Design Arena: agents building full-stack appsAgentic work | 1068 | Not in index |
| Design Arena: agents building mobile appsAgentic work | 1093 | Not in index |
| Design Arena: agents building Android appsAgentic work | 1065 | Not in index |
| Design Arena: agents building Godot gamesAgentic work | 1236 | Not in index |
| Design Arena: agents building gamesAgentic work | 1114 | Not in index |
| Design Arena: HTML slidesAgentic work | 1153 | Not in index |
| Design Arena: PowerPoint slidesAgentic work | 1063 | 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 | Not measured | Not in index |
| LiveBench data analysisGeneral | Not measured | Not in index |
| LiveBench researchAgentic work | Not measured | Not in index |
| LiveBench browserAgentic work | Not measured | Not in index |
| LiveBench long agenticAgentic work | Not measured | Not in index |
| LiveBench designWeb design | Not measured | Not in index |
| LiveCodeBench (Vals AI)Coding | 88.5% | Not in index |
| SWE-bench Verified (Vals AI)Coding | 78.8% | Not in index |
| Terminal-Bench 4 (Vals AI)Coding | 2.5% | Not in index |
| Vibe Code Bench (Vals AI)Coding | 32.0% | Not in index |
| Code migration (Vals AI)Coding | 17.3% | Not in index |
| ProgramBench (Vals AI)Coding | 0.0% | Not in index |
| SREBench (Vals AI)Agentic work | 0.0% | Not in index |
| IOI (Vals AI)Coding | 51.8% | Not in index |
| Terminal-Bench 2.1 (Vals AI)Coding | 70.8% | Not in index |
| SWE-bench Multimodal (Vals AI)Coding | Not measured | Not in index |
| Vibe Code Bench 1-100 (Vals AI)Coding | 6.7% | 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 | 43.0% | Not in index |
| Tax Agent Bench (Vals AI)Agentic work | 9.3% | Not in index |
| Legal Research Bench (Vals AI)Agentic work | 20.7% | Not in index |
| Harvey's Legal Agent Benchmark (Vals AI)Agentic work | Not measured | Not in index |
| Excel Modeling Benchmark (Vals AI)Agentic work | 52.6% | Not in index |
| BioMysteryBench (Vals AI)Agentic work | 60.0% | Not in index |
| Terminal-Bench-Science (Vals AI)Agentic work | 1.4% | Not in index |
| Vals Science IndexAgentic work | 27.4% | 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 | 53.8% | Not in index |
| MysteryMechanism (Vals AI)Reasoning | 20.7% | Not in index |
| MMMU Pro (Vals AI)Reasoning | 88.2% | 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 | 48.7% | Not in index |
| LegalBench (Vals AI)Knowledge | 87.4% | Not in index |
| CaseLaw (Vals AI)Knowledge | 64.8% | Not in index |
| CorpFin (Vals AI)Knowledge | 64.5% | Not in index |
| TaxEval (Vals AI)Knowledge | 72.9% | Not in index |
| MortgageTax (Vals AI)Knowledge | 69.4% | Not in index |
| MedQA (Vals AI)Knowledge | 96.4% | Not in index |
| MedCode (Vals AI)Knowledge | 59.1% | Not in index |
| MedScribe (Vals AI)General | 76.1% | Not in index |
| Vals Multimodal IndexGeneral | 56.1% | Not in index |
| AA Math IndexMath | Not measured | Not in index |
| GPQA Diamond (Artificial Analysis run)Reasoning | 94.1% | Not in index |
| Humanity's Last Exam (Artificial Analysis run)Reasoning | 47.0% | 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 | 58.7% | Not in index |
| Terminal-Bench Hard (Artificial Analysis run)Coding | 53.8% | Not in index |
| IFBenchGeneral | 77.1% | Not in index |
| Long context reasoning (AA-LCR)General | 82.0% | Not in index |
| τ²-Bench TelecomAgentic work | 95.6% | Not in index |
| AIME 2025 (Artificial Analysis run)Math | Not measured | Not in index |
| Terminal-BenchCoding | 80.2% | Not in index |
| DeepSWECoding | 11.7% | Not in index |
| FrontierCodeCoding | Not measured | Not in index |
| FrontierSWECoding | Not measured | Not in index |
| GSO-BenchCoding | 22.6% | Not in index |
| WeirdMLCoding | 72.1% | Not in index |
| MirrorCodeCoding | 8.9% | Not in index |
| APEX-AgentsAgentic work | 35.1% | Not in index |
| METR time horizonsAgentic work | 77.0% | 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 | 57.0% | Not in index |
| DeepResearch BenchAgentic work | 47.8% | Not in index |
| PostTrainBenchAgentic work | 22.0% | Not in index |
| GPQA Diamond (Epoch AI run)Reasoning | 94.4% | Not in index |
| ARC-AGIReasoning | 98.0% | Not in index |
| ARC-AGI-2Reasoning | 77.1% | Not in index |
| Humanity's Last ExamReasoning | 46.4% | Not in index |
| SimpleBenchReasoning | 79.6% | Not in index |
| Chess puzzlesReasoning | 51.0% | Not in index |
| Mystery game puzzlesReasoning | 34.0% | Not in index |
| EBR-benchReasoning | 14.3% | Not in index |
| OTIS Mock AIMEMath | 95.6% | Not in index |
| FrontierMath, tiers 1 to 3Math | 59.6% | Not in index |
| FrontierMath, tier 4Math | 26.8% | 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 | 73.5% | Not in index |
| MMLUKnowledge | Not measured | Not in index |
| GeoBenchKnowledge | Not measured | Not in index |
| DTBenchGeneral | 97.1% | Not in index |
| LMCAGeneral | 53.8% | Not in index |
| Fiction.LiveBenchGeneral | Not measured | Not in index |
| Creative writing (Lech Mazur)General | Not measured | Not in index |
| CL-benchGeneral | 20.8% | Not in index |
| Surface Evolver BenchGeneral | Not measured | Not in index |
| Furniture assemblyGeneral | 26.7% | Not in index |
| ExploitBenchGeneral | 26.1% | 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 | 16.9% | Not in index |
| ALE-BenchCoding | 1160.6 | Not in index |
| Vending-Bench 2Agentic work | $911 | Not in index |
| Epoch Capabilities IndexIntelligence | Not measured | Not in index |
| LMArena TextGeneral | 1480 | Not in index |
| LMArena Text: codingCoding | 1484 | Not in index |
| LMArena Text: hard promptsReasoning | 1485 | Not in index |
| LMArena Text: mathMath | 1485 | Not in index |
| LMArena Text: instruction followingGeneral | 1466 | Not in index |
| LMArena Text: creative writingGeneral | 1482 | Not in index |
| LMArena VisionGeneral | 1296 | Not in index |
| LMArena Text: EnglishGeneral | 1478 | Not in index |
| LMArena Text: non-EnglishGeneral | 1476 | Not in index |
| LMArena Text: ChineseGeneral | 1528 | Not in index |
| LMArena Text: GermanGeneral | 1491 | Not in index |
| LMArena Text: JapaneseGeneral | 1493 | Not in index |
| LMArena Text: KoreanGeneral | 1454 | Not in index |
| LMArena Text: FrenchGeneral | 1486 | Not in index |
| LMArena Text: SpanishGeneral | 1480 | Not in index |
| LMArena Text: RussianGeneral | 1497 | Not in index |
| LMArena Text: PolishGeneral | 1497 | Not in index |
| LMArena Text: multi-turnGeneral | 1486 | Not in index |
| LMArena Text: longer queriesGeneral | 1483 | Not in index |
| LMArena Text: expertReasoning | 1483 | Not in index |
| LMArena Text: hard prompts in EnglishReasoning | 1480 | Not in index |
| LMArena Text: software and ITCoding | 1487 | Not in index |
| LMArena Text: mathematical workMath | 1478 | Not in index |
| LMArena Text: scienceKnowledge | 1497 | Not in index |
| LMArena Text: medicine and healthcareKnowledge | 1486 | Not in index |
| LMArena Text: legal and governmentKnowledge | 1486 | Not in index |
| LMArena Text: business and financeKnowledge | 1460 | Not in index |
| LMArena Text: writing and languageGeneral | 1481 | Not in index |
| LMArena Text: entertainment and mediaGeneral | 1466 | Not in index |
| LMArena WebDev: ReactCoding | 1438 | Not in index |
| LMArena WebDev: HTMLCoding | 1490 | Not in index |
| LMArena WebDev: from an imageCoding | 1481 | Not in index |
| LMArena Vision: EnglishGeneral | 1287 | Not in index |
| LMArena Vision: ChineseGeneral | 1364 | Not in index |
| LMArena Vision: reading textGeneral | 1304 | Not in index |
| LMArena Vision: diagramsReasoning | 1311 | Not in index |
| LMArena Vision: homeworkReasoning | 1316 | Not in index |
| LMArena Vision: humorGeneral | 1322 | Not in index |
| LMArena Vision: captioningGeneral | 1345 | Not in index |
| LMArena Vision: recognizing thingsGeneral | 1330 | Not in index |
| LMArena Vision: creative writingGeneral | 1324 | Not in index |
| LMArena SearchAgentic work | Not measured | Not in index |
| LMArena DocumentGeneral | 1444 | 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 |
|---|---|---|---|
| SWE-bench Verified (Vals AI) | 78.8% | $0.78 per test | Duration, as printed 5m 12s |
| Terminal-Bench 4 (Vals AI) | 2.5% | $4.11 per test | Duration, as printed 18m 44s |
| Vibe Code Bench (Vals AI) | 32.0% | $3.83 per test | Duration, as printed 20m 12s |
| Code migration (Vals AI) | 17.3% | $1.61 per test | Duration, as printed 12m 01s |
| ProgramBench (Vals AI) | 0.0% | $2.63 per test | Duration, as printed 12m 36s |
| SREBench (Vals AI) | 0.0% | $11.34 per test | Duration, as printed 1h 03m |
| IOI (Vals AI) | 51.8% | $1.25 per test | Duration, as printed 12m 03s |
| Terminal-Bench 2.1 (Vals AI) | 70.8% | $0.58 per test | Duration, as printed 6m 50s |
| Vibe Code Bench 1-100 (Vals AI) | 6.7% | $3.36 per test | Duration, as printed 11m 28s |
| Finance Agent (Vals AI) | 43.0% | $1.59 per test | Duration, as printed 3m 28s |
| Tax Agent Bench (Vals AI) | 9.3% | $0.30 per test | Duration, as printed 1m 41s |
| Legal Research Bench (Vals AI) | 20.7% | $1.10 per test | Duration, as printed 4m 02s |
| Excel Modeling Benchmark (Vals AI) | 52.6% | $3.77 per test | Duration, as printed 11m 49s |
|---|---|---|---|
| BioMysteryBench (Vals AI) | 60.0% | $0.71 per test | Duration, as printed 4m 12s |
| Terminal-Bench-Science (Vals AI) | 1.4% | $5.91 per test | Duration, as printed 43m 58s |
| Vals Science Index | 27.4% | $2.56 per test | Duration, as printed 18m 03s |
| Public Benefits Bench (Vals AI) | 53.8% | $0.38 per test | Nothing else |
| MysteryMechanism (Vals AI) | 20.7% | $1.07 per test | Duration, as printed 6m 00s |
| Vals Multimodal Index | 56.1% | $0.98 per test | Duration, as printed 5m 23s |
| DeepSWE | 11.7% | $2.1434 mean cost per task | Solved in 4 tries 28.3% · Output tokens per task 28,369 · Agent steps per task 76 |
| WeirdML | 72.1% | $1.3602 per run | Median lines of code 212 |
| ARC-AGI | 98.0% | $0.5223 per task | Nothing else |
| ARC-AGI-2 | 77.1% | $0.9622 per task | Nothing else |
| ProofBench | 26.0% | $0.7843 per test | Time per proof 14m 49s |
| ALE-Bench | 1160.6 | $0.3884 per problem | Tokens per problem 35,084 |
| LMArena WebDev | 1447 Elo | Not published | Votes 24,199 · Interval (±) ±5.1 |
| GPQA Diamond | 95.5% | Not published | Latency, as printed 1m 06s |
| AIME | 98.1% | Not published | Latency, as printed 1m 45s |
| MMLU Pro | 91.0% | Not published | Latency, as printed 24 s |
| Design Arena: websites | 1234 Elo | Not published | Battles 28,255 |
| Design Arena: UI components | 1227 Elo | Not published | Battles 3,328 |
| Design Arena: game dev | 1202 Elo | Not published | Battles 7,074 |
| Design Arena: data viz | 1209 Elo | Not published | Battles 2,418 |
| Design Arena: 3D | 1234 Elo | Not published | Battles 9,108 |
| Design Arena: all code categories | 1231 Elo | Not published | Battles 47,245 |
| Design Arena: SVG | 1284 Elo | Not published | Battles 4,620 |
| Design Arena: ASCII art | 1270 Elo | Not published | Battles 1,358 |
| Design Arena: agents building web apps | 1126 Elo | Not published | Battles 6,609 |
| Design Arena: agents building full-stack apps | 1068 Elo | Not published | Battles 4,827 |
| Design Arena: agents building mobile apps | 1093 Elo | Not published | Battles 2,911 |
| Design Arena: agents building Android apps | 1065 Elo | Not published | Battles 5,361 |
| Design Arena: agents building games | 1114 Elo | Not published | Battles 1,862 |
| Design Arena: HTML slides | 1153 Elo | Not published | Battles 1,979 |
| Design Arena: PowerPoint slides | 1063 Elo | Not published | Battles 1,341 |
| LiveCodeBench (Vals AI) | 88.5% | Not published | Latency, as printed 1m 29s |
| MMMU Pro (Vals AI) | 88.2% | Not published | Latency, as printed 1m 17s |
| SAGE (Vals AI) | 48.7% | Not published | Latency, as printed 1m 01s |
| LegalBench (Vals AI) | 87.4% | Not published | Latency, as printed 10 s |
| CaseLaw (Vals AI) | 64.8% | Not published | Latency, as printed 57 s |
| CorpFin (Vals AI) | 64.5% | Not published | Latency, as printed 25 s |
| TaxEval (Vals AI) | 72.9% | Not published | Latency, as printed 42 s |
| MortgageTax (Vals AI) | 69.4% | Not published | Latency, as printed 24 s |
| MedQA (Vals AI) | 96.4% | Not published | Latency, as printed 39 s |
| MedCode (Vals AI) | 59.1% | Not published | Latency, as printed 39 s |
| MedScribe (Vals AI) | 76.1% | Not published | Latency, as printed 1m 09s |
| APEX-Agents | 35.1% | Not published | Mean score 52.2% |
| LMArena Text | 1480 Elo | Not published | Votes 127,649 · Interval (±) ±3.0 |
| LMArena Text: coding | 1484 Elo | Not published | Votes 35,033 · Interval (±) ±4.5 |
| LMArena Text: hard prompts | 1485 Elo | Not published | Votes 82,971 · Interval (±) ±3.6 |
| LMArena Text: math | 1485 Elo | Not published | Votes 6,622 · Interval (±) ±8.0 |
| LMArena Text: instruction following | 1466 Elo | Not published | Votes 43,642 · Interval (±) ±4.3 |
| LMArena Text: creative writing | 1482 Elo | Not published | Votes 23,619 · Interval (±) ±5.3 |
| LMArena Vision | 1296 Elo | Not published | Votes 47,114 · Interval (±) ±5.1 |
| LMArena Text: English | 1478 Elo | Not published | Votes 56,117 · Interval (±) ±3.9 |
| LMArena Text: non-English | 1476 Elo | Not published | Votes 71,523 · Interval (±) ±3.6 |
| LMArena Text: Chinese | 1528 Elo | Not published | Votes 8,789 · Interval (±) ±7.3 |
| LMArena Text: German | 1491 Elo | Not published | Votes 2,125 · Interval (±) ±14.3 |
| LMArena Text: Japanese | 1493 Elo | Not published | Votes 1,526 · Interval (±) ±17.5 |
| LMArena Text: Korean | 1454 Elo | Not published | Votes 2,263 · Interval (±) ±14.3 |
| LMArena Text: French | 1486 Elo | Not published | Votes 4,197 · Interval (±) ±11.2 |
| LMArena Text: Spanish | 1480 Elo | Not published | Votes 4,053 · Interval (±) ±10.7 |
| LMArena Text: Russian | 1497 Elo | Not published | Votes 14,555 · Interval (±) ±5.9 |
| LMArena Text: Polish | 1497 Elo | Not published | Votes 2,442 · Interval (±) ±12.4 |
| LMArena Text: multi-turn | 1486 Elo | Not published | Votes 21,640 · Interval (±) ±5.3 |
| LMArena Text: longer queries | 1483 Elo | Not published | Votes 56,414 · Interval (±) ±4.2 |
| LMArena Text: expert | 1483 Elo | Not published | Votes 13,288 · Interval (±) ±6.2 |
| LMArena Text: hard prompts in English | 1480 Elo | Not published | Votes 37,273 · Interval (±) ±4.5 |
| LMArena Text: software and IT | 1487 Elo | Not published | Votes 50,148 · Interval (±) ±4.0 |
| LMArena Text: mathematical work | 1478 Elo | Not published | Votes 7,155 · Interval (±) ±7.9 |
| LMArena Text: science | 1497 Elo | Not published | Votes 21,312 · Interval (±) ±5.2 |
| LMArena Text: medicine and healthcare | 1486 Elo | Not published | Votes 9,525 · Interval (±) ±7.1 |
| LMArena Text: legal and government | 1486 Elo | Not published | Votes 10,501 · Interval (±) ±6.7 |
| LMArena Text: business and finance | 1460 Elo | Not published | Votes 24,753 · Interval (±) ±5.0 |
| LMArena Text: writing and language | 1481 Elo | Not published | Votes 32,660 · Interval (±) ±4.7 |
| LMArena Text: entertainment and media | 1466 Elo | Not published | Votes 29,563 · Interval (±) ±4.9 |
| LMArena WebDev: React | 1438 Elo | Not published | Votes 18,253 · Interval (±) ±5.6 |
| LMArena WebDev: HTML | 1490 Elo | Not published | Votes 2,621 · Interval (±) ±12.2 |
| LMArena WebDev: from an image | 1481 Elo | Not published | Votes 8,219 · Interval (±) ±8.7 |
| LMArena Vision: English | 1287 Elo | Not published | Votes 18,497 · Interval (±) ±7.0 |
| LMArena Vision: Chinese | 1364 Elo | Not published | Votes 3,186 · Interval (±) ±13.3 |
| LMArena Vision: reading text | 1304 Elo | Not published | Votes 32,719 · Interval (±) ±5.0 |
| LMArena Vision: diagrams | 1311 Elo | Not published | Votes 12,416 · Interval (±) ±6.9 |
| LMArena Vision: homework | 1316 Elo | Not published | Votes 6,293 · Interval (±) ±8.4 |
| LMArena Vision: humor | 1322 Elo | Not published | Votes 1,885 · Interval (±) ±14.2 |
| LMArena Vision: captioning | 1345 Elo | Not published | Votes 137 · Interval (±) ±48.5 |
| LMArena Vision: recognizing things | 1330 Elo | Not published | Votes 388 · Interval (±) ±28.9 |
| LMArena Vision: creative writing | 1324 Elo | Not published | Votes 3,296 · Interval (±) ±11.2 |
| LMArena Document | 1444 Elo | Not published | Votes 49,457 · Interval (±) ±5.2 |