As of October 20, 2026, Google Gemini 3.6 Flash ranks #41 of 213 models overall with 34.0 on the Artificial Analysis Intelligence Index. Its strongest category is reasoning, where it ranks #15 of 203. Google Gemini 3.6 Flash costs $0.75 per million input tokens and $3.75 per million output tokens. It was released on July 21, 2026.
Its output price ranks 240 of 349 priced models, counting from the cheapest.
Gemini 3.6 Flash is a high-efficiency model from Google for coding, agentic workflows, and web and app development. It is designed to produce polished outputs with fewer unnecessary edits and...
google/gemini-3.6-flash 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, Terminal-Bench 4 (Vals AI), SWE-bench Multimodal (Vals AI), Vibe Code Bench 1-100 (Vals AI), SkillsBench (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 Godot games, LiveBench research, LiveBench browser, LiveBench long agentic, SREBench (Vals AI), Harvey's Legal Agent Benchmark (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 LiveBench reasoning, MysteryMechanism (Vals AI), 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 CaseLaw (Vals AI), MedQA (Vals AI), MMLU Pro (Artificial Analysis run), MMLU, GeoBench, AI2 Reasoning Challenge
Not measured on Design Arena: SVG, LiveBench design
Not measured on Vals Index, LiveBench data analysis, IFBench, Fiction.LiveBench, Creative writing (Lech Mazur), CL-bench, Surface Evolver 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 | Not measured | 20% |
| LMArena WebDevCoding | 1538 | 15% |
| Vals IndexGeneral | Not measured | Not in index |
| GPQA DiamondReasoning | 93.4% | Not in index |
| AIMEMath | Not measured | Not in index |
| MMLU ProKnowledge | 89.3% | Not in index |
| AA Intelligence IndexIntelligence | 34.0 | Not in index |
| AA Coding IndexCoding | 69.2 | Not in index |
| AA Agentic IndexAgentic work | 29.0 | Not in index |
| Design Arena: websitesWeb design | 1300 | Not in index |
| Design Arena: UI componentsWeb design | 1297 | Not in index |
| Design Arena: game devWeb design | 1263 | Not in index |
| Design Arena: data vizWeb design | 1289 | Not in index |
| Design Arena: 3DWeb design | 1272 | Not in index |
| Design Arena: all code categoriesWeb design | 1290 | Not in index |
| Design Arena: SVGWeb design | Not measured | Not in index |
| Design Arena: ASCII artWeb design | 1279 | Not in index |
| Design Arena: agents building web appsAgentic work | 1195 | Not in index |
| Design Arena: agents building full-stack appsAgentic work | 1181 | Not in index |
| Design Arena: agents building mobile appsAgentic work | 1197 | Not in index |
| Design Arena: agents building Android appsAgentic work | 1218 | Not in index |
| Design Arena: agents building Godot gamesAgentic work | Not measured | Not in index |
| Design Arena: agents building gamesAgentic work | 1180 | Not in index |
| Design Arena: HTML slidesAgentic work | 1148 | Not in index |
| Design Arena: PowerPoint slidesAgentic work | 1145 | Not in index |
| Design Arena: spreadsheetsAgentic work | 1156 | 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 | 88.1% | Not in index |
| SWE-bench Verified (Vals AI)Coding | 79.6% | Not in index |
| Terminal-Bench 4 (Vals AI)Coding | Not measured | Not in index |
| Vibe Code Bench (Vals AI)Coding | 64.0% | Not in index |
| Code migration (Vals AI)Coding | 30.9% | Not in index |
| ProgramBench (Vals AI)Coding | 0.0% | Not in index |
| SREBench (Vals AI)Agentic work | Not measured | Not in index |
| IOI (Vals AI)Coding | 35.1% | Not in index |
| Terminal-Bench 2.1 (Vals AI)Coding | 73.8% | 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 | 45.4% | Not in index |
| Finance Agent (Vals AI)Agentic work | 56.3% | Not in index |
| Tax Agent Bench (Vals AI)Agentic work | 18.0% | Not in index |
| Legal Research Bench (Vals AI)Agentic work | 25.0% | Not in index |
| Harvey's Legal Agent Benchmark (Vals AI)Agentic work | Not measured | Not in index |
| Excel Modeling Benchmark (Vals AI)Agentic work | 65.4% | Not in index |
| BioMysteryBench (Vals AI)Agentic work | 58.5% | Not in index |
| Terminal-Bench-Science (Vals AI)Agentic work | 4.3% | 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 | 56.6% | Not in index |
| MysteryMechanism (Vals AI)Reasoning | Not measured | Not in index |
| MMMU Pro (Vals AI)Reasoning | 88.4% | 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 | 86.7% | Not in index |
| CaseLaw (Vals AI)Knowledge | Not measured | Not in index |
| CorpFin (Vals AI)Knowledge | 63.3% | Not in index |
| TaxEval (Vals AI)Knowledge | 74.9% | Not in index |
| MortgageTax (Vals AI)Knowledge | 67.6% | Not in index |
| MedQA (Vals AI)Knowledge | Not measured | Not in index |
| MedCode (Vals AI)Knowledge | 53.1% | Not in index |
| MedScribe (Vals AI)General | 79.7% | Not in index |
| Vals Multimodal IndexGeneral | 65.1% | Not in index |
| AA Math IndexMath | Not measured | Not in index |
| GPQA Diamond (Artificial Analysis run)Reasoning | 92.8% | Not in index |
| Humanity's Last Exam (Artificial Analysis run)Reasoning | 40.8% | 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 | 53.4% | 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 | 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 | 46.7% | Not in index |
| FrontierCodeCoding | 34.4% | Not in index |
| FrontierSWECoding | Not measured | Not in index |
| GSO-BenchCoding | Not measured | Not in index |
| WeirdMLCoding | 56.1% | Not in index |
| MirrorCodeCoding | Not measured | Not in index |
| APEX-AgentsAgentic work | 46.9% | 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 | 94.1% | Not in index |
| ARC-AGIReasoning | 91.2% | Not in index |
| ARC-AGI-2Reasoning | 60.4% | Not in index |
| Humanity's Last ExamReasoning | Not measured | Not in index |
| SimpleBenchReasoning | Not measured | Not in index |
| Chess puzzlesReasoning | 42.0% | Not in index |
| Mystery game puzzlesReasoning | 30.0% | Not in index |
| EBR-benchReasoning | Not measured | Not in index |
| OTIS Mock AIMEMath | 94.2% | Not in index |
| FrontierMath, tiers 1 to 3Math | 58.9% | Not in index |
| FrontierMath, tier 4Math | 22.0% | Not in index |
| ProofBenchMath | 36.0% | Not in index |
| MATH level 5Math | Not measured | Not in index |
| GSM8KMath | Not measured | Not in index |
| SimpleQA VerifiedKnowledge | 66.2% | Not in index |
| MMLUKnowledge | Not measured | Not in index |
| GeoBenchKnowledge | Not measured | Not in index |
| DTBenchGeneral | 95.5% | Not in index |
| LMCAGeneral | 44.9% | 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 | 23.3% | 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 | 715.5 | Not in index |
| Vending-Bench 2Agentic work | Not measured | Not in index |
| Epoch Capabilities IndexIntelligence | 154.2 | Not in index |
| LMArena TextGeneral | 1479 | Not in index |
| LMArena Text: codingCoding | 1491 | Not in index |
| LMArena Text: hard promptsReasoning | 1485 | Not in index |
| LMArena Text: mathMath | 1506 | Not in index |
| LMArena Text: instruction followingGeneral | 1467 | Not in index |
| LMArena Text: creative writingGeneral | 1466 | Not in index |
| LMArena VisionGeneral | 1299 | Not in index |
| LMArena Text: EnglishGeneral | 1482 | Not in index |
| LMArena Text: non-EnglishGeneral | 1470 | Not in index |
| LMArena Text: ChineseGeneral | 1530 | Not in index |
| LMArena Text: GermanGeneral | 1481 | Not in index |
| LMArena Text: JapaneseGeneral | 1476 | Not in index |
| LMArena Text: KoreanGeneral | 1430 | Not in index |
| LMArena Text: FrenchGeneral | 1502 | Not in index |
| LMArena Text: SpanishGeneral | 1476 | Not in index |
| LMArena Text: RussianGeneral | 1488 | Not in index |
| LMArena Text: PolishGeneral | 1475 | Not in index |
| LMArena Text: multi-turnGeneral | 1481 | Not in index |
| LMArena Text: longer queriesGeneral | 1474 | Not in index |
| LMArena Text: expertReasoning | 1489 | Not in index |
| LMArena Text: hard prompts in EnglishReasoning | 1484 | Not in index |
| LMArena Text: software and ITCoding | 1492 | Not in index |
| LMArena Text: mathematical workMath | 1490 | Not in index |
| LMArena Text: scienceKnowledge | 1488 | Not in index |
| LMArena Text: medicine and healthcareKnowledge | 1468 | Not in index |
| LMArena Text: legal and governmentKnowledge | 1480 | Not in index |
| LMArena Text: business and financeKnowledge | 1464 | Not in index |
| LMArena Text: writing and languageGeneral | 1470 | Not in index |
| LMArena Text: entertainment and mediaGeneral | 1456 | Not in index |
| LMArena WebDev: ReactCoding | 1528 | Not in index |
| LMArena WebDev: HTMLCoding | 1547 | Not in index |
| LMArena WebDev: from an imageCoding | 1545 | Not in index |
| LMArena Vision: EnglishGeneral | 1295 | Not in index |
| LMArena Vision: ChineseGeneral | 1357 | Not in index |
| LMArena Vision: reading textGeneral | 1312 | Not in index |
| LMArena Vision: diagramsReasoning | 1314 | Not in index |
| LMArena Vision: homeworkReasoning | 1314 | Not in index |
| LMArena Vision: humorGeneral | 1289 | Not in index |
| LMArena Vision: captioningGeneral | Not measured | Not in index |
| LMArena Vision: recognizing thingsGeneral | Not measured | Not in index |
| LMArena Vision: creative writingGeneral | 1278 | Not in index |
| LMArena SearchAgentic work | Not measured | Not in index |
| LMArena DocumentGeneral | 1456 | 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) | 79.6% | $1.19 per test | Duration, as printed 13m 08s |
| Vibe Code Bench (Vals AI) | 64.0% | $3.04 per test | Duration, as printed 25m 23s |
| Code migration (Vals AI) | 30.9% | $8.93 per test | Duration, as printed 1h 30m |
| ProgramBench (Vals AI) | 0.0% | $5.92 per test | Duration, as printed 47m 33s |
| IOI (Vals AI) | 35.1% | $8.67 per test | Duration, as printed 48m 23s |
| Terminal-Bench 2.1 (Vals AI) | 73.8% | $1.17 per test | Duration, as printed 9m 12s |
| CyberBench (Vals AI) | 45.4% | $1.31 per test | Duration, as printed 11m 00s |
| Finance Agent (Vals AI) | 56.3% | $1.40 per test | Duration, as printed 3m 45s |
| Tax Agent Bench (Vals AI) | 18.0% | $0.36 per test | Duration, as printed 1m 45s |
| Legal Research Bench (Vals AI) | 25.0% | $0.47 per test | Duration, as printed 2m 48s |
| Excel Modeling Benchmark (Vals AI) | 65.4% | $3.89 per test | Duration, as printed 12m 06s |
| BioMysteryBench (Vals AI) | 58.5% | $1.25 per test | Duration, as printed 12m 42s |
| Terminal-Bench-Science (Vals AI) | 4.3% | $4.39 per test | Duration, as printed 1h 52m |
|---|---|---|---|
| Public Benefits Bench (Vals AI) | 56.6% | $0.39 per test | Nothing else |
| Vals Multimodal Index | 65.1% | $1.02 per test | Duration, as printed 8m 56s |
| DeepSWE | 46.7% | $4.419 mean cost per task | Solved in 4 tries 75.2% · Output tokens per task 95,845 · Agent steps per task 117 |
| WeirdML | 56.1% | $0.6227 per run | Median lines of code 346 |
| ProofBench | 36.0% | $0.5221 per test | Time per proof 5m 47s |
| ALE-Bench | 715.5 | $0.2445 per problem | Tokens per problem 35,204 |
| LMArena WebDev | 1538 Elo | Not published | Votes 8,762 · Interval (±) ±7.5 |
| GPQA Diamond | 93.4% | Not published | Latency, as printed 18 s |
| MMLU Pro | 89.3% | Not published | Latency, as printed 7.3 s |
| Design Arena: websites | 1300 Elo | Not published | Battles 15,658 |
| Design Arena: UI components | 1297 Elo | Not published | Battles 1,864 |
| Design Arena: game dev | 1263 Elo | Not published | Battles 5,608 |
| Design Arena: data viz | 1289 Elo | Not published | Battles 3,642 |
| Design Arena: 3D | 1272 Elo | Not published | Battles 7,916 |
| Design Arena: all code categories | 1290 Elo | Not published | Battles 32,546 |
| Design Arena: ASCII art | 1279 Elo | Not published | Battles 352 |
| Design Arena: agents building web apps | 1195 Elo | Not published | Battles 2,809 |
| Design Arena: agents building full-stack apps | 1181 Elo | Not published | Battles 2,934 |
| Design Arena: agents building mobile apps | 1197 Elo | Not published | Battles 1,724 |
| Design Arena: agents building Android apps | 1218 Elo | Not published | Battles 2,300 |
| Design Arena: agents building games | 1180 Elo | Not published | Battles 1,695 |
| Design Arena: HTML slides | 1148 Elo | Not published | Battles 1,261 |
| Design Arena: PowerPoint slides | 1145 Elo | Not published | Battles 855 |
| Design Arena: spreadsheets | 1156 Elo | Not published | Battles 36 |
| LiveCodeBench (Vals AI) | 88.1% | Not published | Latency, as printed 32 s |
| MMMU Pro (Vals AI) | 88.4% | Not published | Latency, as printed 11 s |
| SAGE (Vals AI) | 48.7% | Not published | Latency, as printed 22 s |
| LegalBench (Vals AI) | 86.7% | Not published | Latency, as printed 3.0 s |
| CorpFin (Vals AI) | 63.3% | Not published | Latency, as printed 6.3 s |
| TaxEval (Vals AI) | 74.9% | Not published | Latency, as printed 12 s |
| MortgageTax (Vals AI) | 67.6% | Not published | Latency, as printed 9.2 s |
| MedCode (Vals AI) | 53.1% | Not published | Latency, as printed 17 s |
| MedScribe (Vals AI) | 79.7% | Not published | Latency, as printed 34 s |
| APEX-Agents | 46.9% | Not published | Mean score 63.4% |
| LMArena Text | 1479 Elo | Not published | Votes 36,122 · Interval (±) ±4.4 |
| LMArena Text: coding | 1491 Elo | Not published | Votes 10,368 · Interval (±) ±6.8 |
| LMArena Text: hard prompts | 1485 Elo | Not published | Votes 24,166 · Interval (±) ±5.1 |
| LMArena Text: math | 1506 Elo | Not published | Votes 1,764 · Interval (±) ±14.1 |
| LMArena Text: instruction following | 1467 Elo | Not published | Votes 13,124 · Interval (±) ±6.3 |
| LMArena Text: creative writing | 1466 Elo | Not published | Votes 7,583 · Interval (±) ±8.0 |
| LMArena Vision | 1299 Elo | Not published | Votes 8,979 · Interval (±) ±7.9 |
| LMArena Text: English | 1482 Elo | Not published | Votes 15,173 · Interval (±) ±5.8 |
| LMArena Text: non-English | 1470 Elo | Not published | Votes 20,948 · Interval (±) ±5.3 |
| LMArena Text: Chinese | 1530 Elo | Not published | Votes 2,691 · Interval (±) ±11.9 |
| LMArena Text: German | 1481 Elo | Not published | Votes 594 · Interval (±) ±24.4 |
| LMArena Text: Japanese | 1476 Elo | Not published | Votes 618 · Interval (±) ±25.8 |
| LMArena Text: Korean | 1430 Elo | Not published | Votes 708 · Interval (±) ±22.6 |
| LMArena Text: French | 1502 Elo | Not published | Votes 1,150 · Interval (±) ±18.7 |
| LMArena Text: Spanish | 1476 Elo | Not published | Votes 950 · Interval (±) ±20.2 |
| LMArena Text: Russian | 1488 Elo | Not published | Votes 4,166 · Interval (±) ±9.7 |
| LMArena Text: Polish | 1475 Elo | Not published | Votes 532 · Interval (±) ±25.3 |
| LMArena Text: multi-turn | 1481 Elo | Not published | Votes 5,798 · Interval (±) ±8.4 |
| LMArena Text: longer queries | 1474 Elo | Not published | Votes 17,161 · Interval (±) ±5.9 |
| LMArena Text: expert | 1489 Elo | Not published | Votes 4,228 · Interval (±) ±9.5 |
| LMArena Text: hard prompts in English | 1484 Elo | Not published | Votes 10,143 · Interval (±) ±6.8 |
| LMArena Text: software and IT | 1492 Elo | Not published | Votes 14,513 · Interval (±) ±6.0 |
| LMArena Text: mathematical work | 1490 Elo | Not published | Votes 2,148 · Interval (±) ±13.1 |
| LMArena Text: science | 1488 Elo | Not published | Votes 5,824 · Interval (±) ±8.2 |
| LMArena Text: medicine and healthcare | 1468 Elo | Not published | Votes 2,557 · Interval (±) ±12.2 |
| LMArena Text: legal and government | 1480 Elo | Not published | Votes 3,027 · Interval (±) ±11.2 |
| LMArena Text: business and finance | 1464 Elo | Not published | Votes 6,836 · Interval (±) ±7.8 |
| LMArena Text: writing and language | 1470 Elo | Not published | Votes 9,852 · Interval (±) ±7.0 |
| LMArena Text: entertainment and media | 1456 Elo | Not published | Votes 9,313 · Interval (±) ±7.2 |
| LMArena WebDev: React | 1528 Elo | Not published | Votes 5,500 · Interval (±) ±9.1 |
| LMArena WebDev: HTML | 1547 Elo | Not published | Votes 922 · Interval (±) ±20.9 |
| LMArena WebDev: from an image | 1545 Elo | Not published | Votes 1,797 · Interval (±) ±14.3 |
| LMArena Vision: English | 1295 Elo | Not published | Votes 3,098 · Interval (±) ±11.7 |
| LMArena Vision: Chinese | 1357 Elo | Not published | Votes 536 · Interval (±) ±26.1 |
| LMArena Vision: reading text | 1312 Elo | Not published | Votes 6,075 · Interval (±) ±8.4 |
| LMArena Vision: diagrams | 1314 Elo | Not published | Votes 2,285 · Interval (±) ±12.9 |
| LMArena Vision: homework | 1314 Elo | Not published | Votes 993 · Interval (±) ±18.6 |
| LMArena Vision: humor | 1289 Elo | Not published | Votes 427 · Interval (±) ±29.3 |
| LMArena Vision: creative writing | 1278 Elo | Not published | Votes 792 · Interval (±) ±22.0 |
| LMArena Document | 1456 Elo | Not published | Votes 2,975 · Interval (±) ±10.8 |