As of October 20, 2026, Google Gemini 3.8 Flash ranks #24 of 213 models overall with 40.9 on the Artificial Analysis Intelligence Index. Its strongest category is knowledge, where it ranks #5 of 147. Google Gemini 3.8 Flash costs $0.825 per million input tokens and $4.125 per million output tokens. It was released on September 2, 2026.
Its output price ranks 247 of 349 priced models, counting from the cheapest.
Gemini 3.8 Flash is Google's most intelligent Flash model with significant gains from 3.7 Flash across software engineering, agentic tasks, and multi-step reasoning.
google/gemini-3.8-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, LiveCodeBench (Artificial Analysis run), Terminal-Bench Hard (Artificial Analysis run), Terminal-Bench, GSO-Bench, MirrorCode, Cybench
Not measured on Design Arena: agents building games, Design Arena: HTML slides, Robo-bench (Vals AI), τ²-Bench Telecom, METR time horizons, GDPval, OSWorld 2.0, BALROG, DeepResearch Bench, PostTrainBench, TheAgentCompany, OSWorld, SpireClimb, LMArena Search
Not measured on 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), CorpFin (Vals AI), MedQA (Vals AI), MMLU Pro (Artificial Analysis run), MMLU, GeoBench, AI2 Reasoning Challenge
Not measured on Vals Multimodal Index, IFBench, Fiction.LiveBench, Creative writing (Lech Mazur), CL-bench, ExploitBench, HellaSwag, WinoGrande, PIQA, CL-bench Life, 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 | 82.2% | 20% |
| LMArena WebDevCoding | 1585 | 15% |
| Vals IndexGeneral | 56.0% | Not in index |
| GPQA DiamondReasoning | 94.4% | Not in index |
| AIMEMath | Not measured | Not in index |
| MMLU ProKnowledge | 90.2% | Not in index |
| AA Intelligence IndexIntelligence | 40.9 | Not in index |
| AA Coding IndexCoding | 76.3 | Not in index |
| AA Agentic IndexAgentic work | 40.2 | Not in index |
| Design Arena: websitesWeb design | 1301 | Not in index |
| Design Arena: UI componentsWeb design | 1318 | Not in index |
| Design Arena: game devWeb design | 1305 | Not in index |
| Design Arena: data vizWeb design | 1271 | Not in index |
| Design Arena: 3DWeb design | 1295 | Not in index |
| Design Arena: all code categoriesWeb design | 1304 | Not in index |
| Design Arena: SVGWeb design | 1294 | Not in index |
| Design Arena: ASCII artWeb design | 1262 | Not in index |
| Design Arena: agents building web appsAgentic work | 1236 | Not in index |
| Design Arena: agents building full-stack appsAgentic work | 1244 | Not in index |
| Design Arena: agents building mobile appsAgentic work | 1235 | Not in index |
| Design Arena: agents building Android appsAgentic work | 1078 | Not in index |
| Design Arena: agents building Godot gamesAgentic work | 1273 | 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 | 1179 | Not in index |
| Design Arena: spreadsheetsAgentic work | 1138 | 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 | 89.3% | Not in index |
| LiveBench data analysisGeneral | 54.0% | Not in index |
| LiveBench researchAgentic work | 79.1% | Not in index |
| LiveBench browserAgentic work | 64.0% | Not in index |
| LiveBench long agenticAgentic work | 30.1% | Not in index |
| LiveBench designWeb design | 72.7% | Not in index |
| LiveCodeBench (Vals AI)Coding | 89.5% | Not in index |
| SWE-bench Verified (Vals AI)Coding | 80.0% | Not in index |
| Terminal-Bench 4 (Vals AI)Coding | 19.7% | Not in index |
| Vibe Code Bench (Vals AI)Coding | 78.7% | Not in index |
| Code migration (Vals AI)Coding | 36.5% | Not in index |
| ProgramBench (Vals AI)Coding | 1.0% | Not in index |
| SREBench (Vals AI)Agentic work | 11.1% | Not in index |
| IOI (Vals AI)Coding | 56.9% | Not in index |
| Terminal-Bench 2.1 (Vals AI)Coding | 81.3% | Not in index |
| SWE-bench Multimodal (Vals AI)Coding | 40.8% | Not in index |
| Vibe Code Bench 1-100 (Vals AI)Coding | 18.8% | Not in index |
| SkillsBench (Vals AI)Coding | 58.0% | Not in index |
| CyberBench (Vals AI)Coding | 43.8% | Not in index |
| Finance Agent (Vals AI)Agentic work | 61.4% | Not in index |
| Tax Agent Bench (Vals AI)Agentic work | 32.1% | Not in index |
| Legal Research Bench (Vals AI)Agentic work | 38.9% | Not in index |
| Harvey's Legal Agent Benchmark (Vals AI)Agentic work | 12.1% | Not in index |
| Excel Modeling Benchmark (Vals AI)Agentic work | 72.2% | Not in index |
| BioMysteryBench (Vals AI)Agentic work | 62.2% | Not in index |
| Terminal-Bench-Science (Vals AI)Agentic work | 8.6% | Not in index |
| Vals Science IndexAgentic work | 35.8% | Not in index |
| Time Horizon Index (Vals AI)Agentic work | 18.8% | Not in index |
| CUA-bench (Vals AI)Agentic work | 4.2% | Not in index |
| Robo-bench (Vals AI)Agentic work | Not measured | Not in index |
| Public Benefits Bench (Vals AI)General | 65.3% | Not in index |
| MysteryMechanism (Vals AI)Reasoning | 36.5% | Not in index |
| MMMU Pro (Vals AI)Reasoning | 89.1% | 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 | 35.1% | Not in index |
| LegalBench (Vals AI)Knowledge | 87.0% | 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 | 74.5% | Not in index |
| MortgageTax (Vals AI)Knowledge | 65.3% | Not in index |
| MedQA (Vals AI)Knowledge | Not measured | Not in index |
| MedCode (Vals AI)Knowledge | 48.1% | Not in index |
| MedScribe (Vals AI)General | 84.5% | 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 | 95.3% | Not in index |
| Humanity's Last Exam (Artificial Analysis run)Reasoning | 47.8% | 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 | 56.6% | 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 | 84.0% | 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 | 73.8% | Not in index |
| FrontierCodeCoding | 41.2% | Not in index |
| FrontierSWECoding | 19.6% | Not in index |
| GSO-BenchCoding | Not measured | Not in index |
| WeirdMLCoding | 84.8% | Not in index |
| MirrorCodeCoding | Not measured | Not in index |
| APEX-AgentsAgentic work | 64.3% | Not in index |
| METR time horizonsAgentic work | Not measured | Not in index |
| Remote Labor IndexAgentic work | 5.8% | 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 | 95.4% | Not in index |
| ARC-AGIReasoning | 98.5% | Not in index |
| ARC-AGI-2Reasoning | 89.2% | Not in index |
| Humanity's Last ExamReasoning | 44.5% | Not in index |
| SimpleBenchReasoning | Not measured | Not in index |
| Chess puzzlesReasoning | 58.0% | Not in index |
| Mystery game puzzlesReasoning | 47.0% | Not in index |
| EBR-benchReasoning | Not measured | Not in index |
| OTIS Mock AIMEMath | 98.9% | Not in index |
| FrontierMath, tiers 1 to 3Math | 68.4% | Not in index |
| FrontierMath, tier 4Math | 22.0% | Not in index |
| ProofBenchMath | 48.0% | Not in index |
| MATH level 5Math | Not measured | Not in index |
| GSM8KMath | Not measured | Not in index |
| SimpleQA VerifiedKnowledge | 69.7% | Not in index |
| MMLUKnowledge | Not measured | Not in index |
| GeoBenchKnowledge | Not measured | Not in index |
| DTBenchGeneral | 95.7% | Not in index |
| LMCAGeneral | 52.9% | 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 | 76.9% | Not in index |
| Furniture assemblyGeneral | 31.7% | 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 | 1269.7 | Not in index |
| Vending-Bench 2Agentic work | $5,094 | Not in index |
| Epoch Capabilities IndexIntelligence | 157.2 | Not in index |
| LMArena TextGeneral | 1499 | Not in index |
| LMArena Text: codingCoding | 1507 | Not in index |
| LMArena Text: hard promptsReasoning | 1509 | Not in index |
| LMArena Text: mathMath | 1527 | Not in index |
| LMArena Text: instruction followingGeneral | 1491 | Not in index |
| LMArena Text: creative writingGeneral | 1492 | Not in index |
| LMArena VisionGeneral | 1315 | Not in index |
| LMArena Text: EnglishGeneral | 1499 | Not in index |
| LMArena Text: non-EnglishGeneral | 1491 | Not in index |
| LMArena Text: ChineseGeneral | 1551 | Not in index |
| LMArena Text: GermanGeneral | 1498 | Not in index |
| LMArena Text: JapaneseGeneral | 1506 | Not in index |
| LMArena Text: KoreanGeneral | 1462 | Not in index |
| LMArena Text: FrenchGeneral | 1492 | Not in index |
| LMArena Text: SpanishGeneral | 1486 | Not in index |
| LMArena Text: RussianGeneral | 1514 | Not in index |
| LMArena Text: PolishGeneral | 1498 | Not in index |
| LMArena Text: multi-turnGeneral | 1502 | Not in index |
| LMArena Text: longer queriesGeneral | 1507 | Not in index |
| LMArena Text: expertReasoning | 1525 | Not in index |
| LMArena Text: hard prompts in EnglishReasoning | 1504 | Not in index |
| LMArena Text: software and ITCoding | 1506 | Not in index |
| LMArena Text: mathematical workMath | 1513 | Not in index |
| LMArena Text: scienceKnowledge | 1521 | Not in index |
| LMArena Text: medicine and healthcareKnowledge | 1507 | Not in index |
| LMArena Text: legal and governmentKnowledge | 1499 | Not in index |
| LMArena Text: business and financeKnowledge | 1479 | Not in index |
| LMArena Text: writing and languageGeneral | 1496 | Not in index |
| LMArena Text: entertainment and mediaGeneral | 1480 | Not in index |
| LMArena WebDev: ReactCoding | 1577 | Not in index |
| LMArena WebDev: HTMLCoding | 1616 | Not in index |
| LMArena WebDev: from an imageCoding | 1593 | Not in index |
| LMArena Vision: EnglishGeneral | 1318 | Not in index |
| LMArena Vision: ChineseGeneral | 1416 | Not in index |
| LMArena Vision: reading textGeneral | 1333 | Not in index |
| LMArena Vision: diagramsReasoning | 1345 | Not in index |
| LMArena Vision: homeworkReasoning | 1351 | Not in index |
| LMArena Vision: humorGeneral | 1321 | Not in index |
| LMArena Vision: captioningGeneral | Not measured | Not in index |
| LMArena Vision: recognizing thingsGeneral | Not measured | Not in index |
| LMArena Vision: creative writingGeneral | 1299 | 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 | 82.2% | $2.2964 per task | Output tokens per task 111,470 |
| Vals Index | 56.0% | $6.06 per test | Duration, as printed 35m 58s |
| LiveBench reasoning | 89.3% | $0.1476 per task | Output tokens per task 39,118 |
| LiveBench data analysis | 54.0% | $0.2377 per task | Output tokens per task 62,326 |
| LiveBench research | 79.1% | $2.6381 per task | Output tokens per task 135,968 |
| LiveBench browser | 64.0% | $1.2131 per task | Output tokens per task 36,860 |
| LiveBench long agentic | 30.1% | $7.039 per task | Output tokens per task 284,589 |
| LiveBench design | 72.7% | $0.9796 per task | Output tokens per task 86,732 |
| SWE-bench Verified (Vals AI) | 80.0% | $2.19 per test | Duration, as printed 11m 23s |
| Terminal-Bench 4 (Vals AI) | 19.7% | $8.65 per test | Duration, as printed 1h 47m |
| Vibe Code Bench (Vals AI) | 78.7% | $6.87 per test | Duration, as printed 8m 39s |
| Code migration (Vals AI) | 36.5% | $18.49 per test | Duration, as printed 2h 37m |
| ProgramBench (Vals AI) | 1.0% | $10.93 per test | Duration, as printed 46m 39s |
|---|---|---|---|
| SREBench (Vals AI) | 11.1% | $27.46 per test | Duration, as printed 2h 28m |
| IOI (Vals AI) | 56.9% | $3.98 per test | Duration, as printed 14m 20s |
| Terminal-Bench 2.1 (Vals AI) | 81.3% | $1.54 per test | Duration, as printed 9m 15s |
| SWE-bench Multimodal (Vals AI) | 40.8% | $3.69 per test | Duration, as printed 22m 18s |
| Vibe Code Bench 1-100 (Vals AI) | 18.8% | $18.91 per test | Duration, as printed 1h 06m |
| SkillsBench (Vals AI) | 58.0% | $2.34 per test | Duration, as printed 3m 55s |
| CyberBench (Vals AI) | 43.8% | $1.31 per test | Duration, as printed 9m 49s |
| Finance Agent (Vals AI) | 61.4% | $2.00 per test | Duration, as printed 3m 21s |
| Tax Agent Bench (Vals AI) | 32.1% | $0.86 per test | Duration, as printed 2m 58s |
| Legal Research Bench (Vals AI) | 38.9% | $1.63 per test | Duration, as printed 5m 24s |
| Harvey's Legal Agent Benchmark (Vals AI) | 12.1% | $3.66 per test | Duration, as printed 19m 22s |
| Excel Modeling Benchmark (Vals AI) | 72.2% | $8.24 per test | Duration, as printed 12m 49s |
| BioMysteryBench (Vals AI) | 62.2% | $1.55 per test | Duration, as printed 5m 27s |
| Terminal-Bench-Science (Vals AI) | 8.6% | $5.64 per test | Duration, as printed 55m 11s |
| Vals Science Index | 35.8% | $2.98 per test | Duration, as printed 22m 00s |
| Public Benefits Bench (Vals AI) | 65.3% | $1.01 per test | Nothing else |
| MysteryMechanism (Vals AI) | 36.5% | $1.73 per test | Duration, as printed 5m 22s |
| DeepSWE | 73.8% | $2.3623 mean cost per task | Solved in 4 tries 85.8% · Output tokens per task 143,243 · Agent steps per task 166 |
| FrontierSWE | 19.6% | $38.75 average cost per task | Best of 5 runs 31.6% · Hours per task 7.2 h |
| WeirdML | 84.8% | $0.5073 per run | Median lines of code 439 |
| ProofBench | 48.0% | $0.6029 per test | Time per proof 6m 09s |
| Surface Evolver Bench | 76.9% | $2.5981 of the run | Pass rate 56.3% · Tokens for the run 3.2M |
| ALE-Bench | 1269.7 | $0.3443 per problem | Tokens per problem 48,512 |
| LMArena WebDev | 1585 Elo | Not published | Votes 10,851 · Interval (±) ±7.4 |
| GPQA Diamond | 94.4% | Not published | Latency, as printed 20 s |
| MMLU Pro | 90.2% | Not published | Latency, as printed 7.8 s |
| Design Arena: websites | 1301 Elo | Not published | Battles 29,381 |
| Design Arena: UI components | 1318 Elo | Not published | Battles 1,754 |
| Design Arena: game dev | 1305 Elo | Not published | Battles 12,491 |
| Design Arena: data viz | 1271 Elo | Not published | Battles 513 |
| Design Arena: 3D | 1295 Elo | Not published | Battles 6,286 |
| Design Arena: all code categories | 1304 Elo | Not published | Battles 45,871 |
| Design Arena: SVG | 1294 Elo | Not published | Battles 2,224 |
| Design Arena: ASCII art | 1262 Elo | Not published | Battles 267 |
| Design Arena: agents building web apps | 1236 Elo | Not published | Battles 1,433 |
| Design Arena: agents building full-stack apps | 1244 Elo | Not published | Battles 1,155 |
| Design Arena: agents building mobile apps | 1235 Elo | Not published | Battles 4,206 |
| Design Arena: agents building Android apps | 1078 Elo | Not published | Battles 323 |
| Design Arena: agents building Godot games | 1273 Elo | Not published | Battles 664 |
| Design Arena: PowerPoint slides | 1179 Elo | Not published | Battles 819 |
| Design Arena: spreadsheets | 1138 Elo | Not published | Battles 90 |
| LiveCodeBench (Vals AI) | 89.5% | Not published | Latency, as printed 24 s |
| MMMU Pro (Vals AI) | 89.1% | Not published | Latency, as printed 12 s |
| SAGE (Vals AI) | 35.1% | Not published | Latency, as printed 29 s |
| LegalBench (Vals AI) | 87.0% | Not published | Latency, as printed 3.3 s |
| TaxEval (Vals AI) | 74.5% | Not published | Latency, as printed 8.8 s |
| MortgageTax (Vals AI) | 65.3% | Not published | Latency, as printed 15 s |
| MedCode (Vals AI) | 48.1% | Not published | Latency, as printed 43 s |
| MedScribe (Vals AI) | 84.5% | Not published | Latency, as printed 21 s |
| APEX-Agents | 64.3% | Not published | Mean score 72.9% |
| LMArena Text | 1499 Elo | Not published | Votes 37,454 · Interval (±) ±4.6 |
| LMArena Text: coding | 1507 Elo | Not published | Votes 9,810 · Interval (±) ±7.1 |
| LMArena Text: hard prompts | 1509 Elo | Not published | Votes 24,169 · Interval (±) ±5.5 |
| LMArena Text: math | 1527 Elo | Not published | Votes 1,883 · Interval (±) ±14.1 |
| LMArena Text: instruction following | 1491 Elo | Not published | Votes 13,391 · Interval (±) ±6.5 |
| LMArena Text: creative writing | 1492 Elo | Not published | Votes 8,232 · Interval (±) ±7.9 |
| LMArena Vision | 1315 Elo | Not published | Votes 4,645 · Interval (±) ±9.7 |
| LMArena Text: English | 1499 Elo | Not published | Votes 14,771 · Interval (±) ±6.2 |
| LMArena Text: non-English | 1491 Elo | Not published | Votes 22,675 · Interval (±) ±5.5 |
| LMArena Text: Chinese | 1551 Elo | Not published | Votes 3,070 · Interval (±) ±11.5 |
| LMArena Text: German | 1498 Elo | Not published | Votes 603 · Interval (±) ±24.1 |
| LMArena Text: Japanese | 1506 Elo | Not published | Votes 667 · Interval (±) ±25.9 |
| LMArena Text: Korean | 1462 Elo | Not published | Votes 680 · Interval (±) ±24.6 |
| LMArena Text: French | 1492 Elo | Not published | Votes 1,268 · Interval (±) ±18.2 |
| LMArena Text: Spanish | 1486 Elo | Not published | Votes 1,285 · Interval (±) ±17.1 |
| LMArena Text: Russian | 1514 Elo | Not published | Votes 4,787 · Interval (±) ±9.3 |
| LMArena Text: Polish | 1498 Elo | Not published | Votes 550 · Interval (±) ±25.2 |
| LMArena Text: multi-turn | 1502 Elo | Not published | Votes 5,601 · Interval (±) ±8.7 |
| LMArena Text: longer queries | 1507 Elo | Not published | Votes 17,232 · Interval (±) ±6.2 |
| LMArena Text: expert | 1525 Elo | Not published | Votes 4,424 · Interval (±) ±9.6 |
| LMArena Text: hard prompts in English | 1504 Elo | Not published | Votes 9,477 · Interval (±) ±7.1 |
| LMArena Text: software and IT | 1506 Elo | Not published | Votes 14,131 · Interval (±) ±6.3 |
| LMArena Text: mathematical work | 1513 Elo | Not published | Votes 2,221 · Interval (±) ±13.1 |
| LMArena Text: science | 1521 Elo | Not published | Votes 6,186 · Interval (±) ±8.3 |
| LMArena Text: medicine and healthcare | 1507 Elo | Not published | Votes 2,687 · Interval (±) ±12.3 |
| LMArena Text: legal and government | 1499 Elo | Not published | Votes 3,312 · Interval (±) ±10.9 |
| LMArena Text: business and finance | 1479 Elo | Not published | Votes 6,835 · Interval (±) ±7.9 |
| LMArena Text: writing and language | 1496 Elo | Not published | Votes 10,501 · Interval (±) ±7.1 |
| LMArena Text: entertainment and media | 1480 Elo | Not published | Votes 9,844 · Interval (±) ±7.4 |
| LMArena WebDev: React | 1577 Elo | Not published | Votes 6,947 · Interval (±) ±8.6 |
| LMArena WebDev: HTML | 1616 Elo | Not published | Votes 1,545 · Interval (±) ±17.0 |
| LMArena WebDev: from an image | 1593 Elo | Not published | Votes 2,516 · Interval (±) ±12.6 |
| LMArena Vision: English | 1318 Elo | Not published | Votes 1,556 · Interval (±) ±16.0 |
| LMArena Vision: Chinese | 1416 Elo | Not published | Votes 224 · Interval (±) ±39.3 |
| LMArena Vision: reading text | 1333 Elo | Not published | Votes 3,137 · Interval (±) ±11.2 |
| LMArena Vision: diagrams | 1345 Elo | Not published | Votes 1,159 · Interval (±) ±18.1 |
| LMArena Vision: homework | 1351 Elo | Not published | Votes 681 · Interval (±) ±22.4 |
| LMArena Vision: humor | 1321 Elo | Not published | Votes 175 · Interval (±) ±45.4 |
| LMArena Vision: creative writing | 1299 Elo | Not published | Votes 459 · Interval (±) ±28.8 |