As of October 21, 2026, Qwen3.8 27B ranks #42 of 213 models overall with 33.7 on the Artificial Analysis Intelligence Index. Its strongest category is agentic, where it ranks #14 of 87. Qwen3.8 27B costs $0.04 per million input tokens and $1.35 per million output tokens. It was released on August 14, 2026.
Its output price ranks 162 of 349 priced models, counting from the cheapest.
Qwen3.8 27B is an open-weight dense vision-language model from Qwen. It is suited for coding, professional workflows, research, multimodal interaction, and long-running agent tasks, with flexible thinking that can be...
qwen/qwen3.8-27b 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, Terminal-Bench 4 (Vals AI), SWE-bench Multimodal (Vals AI), Vibe Code Bench 1-100 (Vals AI), LiveCodeBench (Artificial Analysis run), Terminal-Bench Hard (Artificial Analysis run), Terminal-Bench, DeepSWE, FrontierCode, FrontierSWE, GSO-Bench, WeirdML, MirrorCode, Cybench, ALE-Bench
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, SREBench (Vals AI), Harvey's Legal Agent Benchmark (Vals AI), BioMysteryBench (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 MysteryMechanism (Vals AI), GPQA Diamond (Epoch AI run), Humanity's Last Exam, SimpleBench, Chess puzzles, Mystery game puzzles, 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), OTIS Mock AIME, FrontierMath, tiers 1 to 3, FrontierMath, tier 4, MATH level 5, GSM8K
Not measured on CaseLaw (Vals AI), CorpFin (Vals AI), MedQA (Vals AI), MMLU Pro (Artificial Analysis run), SimpleQA Verified, MMLU, GeoBench, AI2 Reasoning Challenge
Not measured on Design Arena: websites, Design Arena: UI components, Design Arena: game dev, Design Arena: data viz, Design Arena: 3D, Design Arena: all code categories, Design Arena: SVG, Design Arena: ASCII art
Not measured on Vals Index, Public Benefits Bench (Vals AI), Vals Multimodal Index, IFBench, Fiction.LiveBench, Creative writing (Lech Mazur), CL-bench, Furniture assembly, 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 | 86.8% | 20% |
| LMArena WebDevCoding | 1593 | 15% |
| Vals IndexGeneral | Not measured | Not in index |
| GPQA DiamondReasoning | 88.9% | Not in index |
| AIMEMath | Not measured | Not in index |
| MMLU ProKnowledge | 84.3% | Not in index |
| AA Intelligence IndexIntelligence | 33.7 | Not in index |
| AA Coding IndexCoding | 68.1 | Not in index |
| AA Agentic IndexAgentic work | 45.8 | Not in index |
| Design Arena: websitesWeb design | Not measured | Not in index |
| Design Arena: UI componentsWeb design | Not measured | Not in index |
| Design Arena: game devWeb design | Not measured | Not in index |
| Design Arena: data vizWeb design | Not measured | Not in index |
| Design Arena: 3DWeb design | Not measured | Not in index |
| Design Arena: all code categoriesWeb design | Not measured | 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 | 80.0% | Not in index |
| LiveBench data analysisGeneral | 76.6% | Not in index |
| LiveBench researchAgentic work | 59.4% | Not in index |
| LiveBench browserAgentic work | 32.0% | Not in index |
| LiveBench long agenticAgentic work | 27.9% | Not in index |
| LiveBench designWeb design | 75.9% | Not in index |
| LiveCodeBench (Vals AI)Coding | 84.0% | Not in index |
| SWE-bench Verified (Vals AI)Coding | 86.0% | Not in index |
| Terminal-Bench 4 (Vals AI)Coding | Not measured | Not in index |
| Vibe Code Bench (Vals AI)Coding | 64.8% | Not in index |
| Code migration (Vals AI)Coding | 14.2% | 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 | 39.1% | Not in index |
| Terminal-Bench 2.1 (Vals AI)Coding | 58.4% | 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 | 38.1% | Not in index |
| CyberBench (Vals AI)Coding | 67.8% | Not in index |
| Finance Agent (Vals AI)Agentic work | 48.5% | Not in index |
| Tax Agent Bench (Vals AI)Agentic work | 30.9% | Not in index |
| Legal Research Bench (Vals AI)Agentic work | 36.1% | Not in index |
| Harvey's Legal Agent Benchmark (Vals AI)Agentic work | Not measured | Not in index |
| Excel Modeling Benchmark (Vals AI)Agentic work | 59.7% | Not in index |
| BioMysteryBench (Vals AI)Agentic work | Not measured | Not in index |
| Terminal-Bench-Science (Vals AI)Agentic work | 0.0% | 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 | Not measured | Not in index |
| MysteryMechanism (Vals AI)Reasoning | Not measured | Not in index |
| MMMU Pro (Vals AI)Reasoning | 83.9% | 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 | 52.4% | Not in index |
| LegalBench (Vals AI)Knowledge | 82.4% | 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 | 70.8% | Not in index |
| MortgageTax (Vals AI)Knowledge | 64.9% | Not in index |
| MedQA (Vals AI)Knowledge | Not measured | Not in index |
| MedCode (Vals AI)Knowledge | 28.7% | Not in index |
| MedScribe (Vals AI)General | 83.8% | 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 | 90.5% | Not in index |
| Humanity's Last Exam (Artificial Analysis run)Reasoning | 33.9% | 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 | 46.6% | 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 | 82.0% | 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 | Not measured | Not in index |
| FrontierSWECoding | Not measured | 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 | 47.5% | 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 | Not measured | Not in index |
| ARC-AGIReasoning | 87.5% | Not in index |
| ARC-AGI-2Reasoning | 42.4% | Not in index |
| Humanity's Last ExamReasoning | Not measured | Not in index |
| SimpleBenchReasoning | Not measured | Not in index |
| Chess puzzlesReasoning | Not measured | Not in index |
| Mystery game puzzlesReasoning | Not measured | Not in index |
| EBR-benchReasoning | Not measured | Not in index |
| OTIS Mock AIMEMath | Not measured | Not in index |
| FrontierMath, tiers 1 to 3Math | Not measured | Not in index |
| FrontierMath, tier 4Math | Not measured | Not in index |
| ProofBenchMath | 16.0% | Not in index |
| MATH level 5Math | Not measured | Not in index |
| GSM8KMath | Not measured | Not in index |
| SimpleQA VerifiedKnowledge | Not measured | Not in index |
| MMLUKnowledge | Not measured | Not in index |
| GeoBenchKnowledge | Not measured | Not in index |
| DTBenchGeneral | 88.0% | Not in index |
| LMCAGeneral | 41.4% | 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 | 45.0% | Not in index |
| Furniture assemblyGeneral | Not measured | 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 | Not measured | Not in index |
| Epoch Capabilities IndexIntelligence | 151.7 | Not in index |
| LMArena TextGeneral | 1440 | Not in index |
| LMArena Text: codingCoding | 1483 | Not in index |
| LMArena Text: hard promptsReasoning | 1459 | Not in index |
| LMArena Text: mathMath | 1455 | Not in index |
| LMArena Text: instruction followingGeneral | 1436 | Not in index |
| LMArena Text: creative writingGeneral | 1383 | Not in index |
| LMArena VisionGeneral | 1269 | Not in index |
| LMArena Text: EnglishGeneral | 1448 | Not in index |
| LMArena Text: non-EnglishGeneral | 1428 | Not in index |
| LMArena Text: ChineseGeneral | 1501 | Not in index |
| LMArena Text: GermanGeneral | 1443 | Not in index |
| LMArena Text: JapaneseGeneral | 1387 | Not in index |
| LMArena Text: KoreanGeneral | 1384 | Not in index |
| LMArena Text: FrenchGeneral | 1465 | Not in index |
| LMArena Text: SpanishGeneral | 1449 | Not in index |
| LMArena Text: RussianGeneral | 1415 | Not in index |
| LMArena Text: PolishGeneral | 1439 | Not in index |
| LMArena Text: multi-turnGeneral | 1440 | Not in index |
| LMArena Text: longer queriesGeneral | 1448 | Not in index |
| LMArena Text: expertReasoning | 1479 | Not in index |
| LMArena Text: hard prompts in EnglishReasoning | 1461 | Not in index |
| LMArena Text: software and ITCoding | 1478 | Not in index |
| LMArena Text: mathematical workMath | 1458 | Not in index |
| LMArena Text: scienceKnowledge | 1467 | Not in index |
| LMArena Text: medicine and healthcareKnowledge | 1437 | Not in index |
| LMArena Text: legal and governmentKnowledge | 1447 | Not in index |
| LMArena Text: business and financeKnowledge | 1438 | Not in index |
| LMArena Text: writing and languageGeneral | 1405 | Not in index |
| LMArena Text: entertainment and mediaGeneral | 1393 | Not in index |
| LMArena WebDev: ReactCoding | 1602 | Not in index |
| LMArena WebDev: HTMLCoding | 1570 | Not in index |
| LMArena WebDev: from an imageCoding | 1577 | Not in index |
| LMArena Vision: EnglishGeneral | 1267 | Not in index |
| LMArena Vision: ChineseGeneral | 1326 | Not in index |
| LMArena Vision: reading textGeneral | 1281 | Not in index |
| LMArena Vision: diagramsReasoning | 1285 | Not in index |
| LMArena Vision: homeworkReasoning | 1295 | Not in index |
| LMArena Vision: humorGeneral | 1235 | Not in index |
| LMArena Vision: captioningGeneral | Not measured | Not in index |
| LMArena Vision: recognizing thingsGeneral | Not measured | Not in index |
| LMArena Vision: creative writingGeneral | 1237 | 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 | 86.8% | $0.69 per task | Output tokens per task 43,464 |
| LiveBench reasoning | 80.0% | $0.0749 per task | Output tokens per task 24,786 |
| LiveBench data analysis | 76.6% | $0.089 per task | Output tokens per task 29,045 |
| LiveBench research | 59.4% | $1.1275 per task | Output tokens per task 84,200 |
| LiveBench browser | 32.0% | $1.2903 per task | Output tokens per task 49,468 |
| LiveBench long agentic | 27.9% | $7.1841 per task | Output tokens per task 366,727 |
| LiveBench design | 75.9% | $0.3836 per task | Output tokens per task 63,352 |
| SWE-bench Verified (Vals AI) | 86.0% | $1.08 per test | Duration, as printed 10m 00s |
| Vibe Code Bench (Vals AI) | 64.8% | $23.46 per test | Duration, as printed 43m 39s |
| Code migration (Vals AI) | 14.2% | $21.68 per test | Duration, as printed 4h 46m |
| ProgramBench (Vals AI) | 0.0% | $17.99 per test | Duration, as printed 5h 57m |
| IOI (Vals AI) | 39.1% | $3.55 per test | Duration, as printed 1h 39m |
| Terminal-Bench 2.1 (Vals AI) | 58.4% | $0.68 per test | Duration, as printed 14m 53s |
|---|---|---|---|
| SkillsBench (Vals AI) | 38.1% | $0.82 per test | Duration, as printed 6m 41s |
| CyberBench (Vals AI) | 67.8% | $0.99 per test | Duration, as printed 41m 36s |
| Finance Agent (Vals AI) | 48.5% | $0.75 per test | Duration, as printed 10m 22s |
| Tax Agent Bench (Vals AI) | 30.9% | $0.82 per test | Duration, as printed 22m 14s |
| Legal Research Bench (Vals AI) | 36.1% | $2.16 per test | Duration, as printed 26m 41s |
| Excel Modeling Benchmark (Vals AI) | 59.7% | $4.56 per test | Duration, as printed 22m 51s |
| Terminal-Bench-Science (Vals AI) | 0.0% | $11.14 per test | Duration, as printed 4h 02m |
| ProofBench | 16.0% | $2.2988 per test | Time per proof 24m 14s |
| Surface Evolver Bench | 45.0% | $9.0488 of the run | Pass rate 18.8% · Tokens for the run 4.7M |
| LMArena WebDev | 1593 Elo | Not published | Votes 16,385 · Interval (±) ±6.5 |
| GPQA Diamond | 88.9% | Not published | Latency, as printed 1m 56s |
| MMLU Pro | 84.3% | Not published | Latency, as printed 1m 10s |
| LiveCodeBench (Vals AI) | 84.0% | Not published | Latency, as printed 2m 29s |
| MMMU Pro (Vals AI) | 83.9% | Not published | Latency, as printed 43 s |
| SAGE (Vals AI) | 52.4% | Not published | Latency, as printed 1m 23s |
| LegalBench (Vals AI) | 82.4% | Not published | Latency, as printed 48 s |
| TaxEval (Vals AI) | 70.8% | Not published | Latency, as printed 1m 34s |
| MortgageTax (Vals AI) | 64.9% | Not published | Latency, as printed 1m 20s |
| MedCode (Vals AI) | 28.7% | Not published | Latency, as printed 1m 29s |
| MedScribe (Vals AI) | 83.8% | Not published | Latency, as printed 1m 30s |
| APEX-Agents | 47.5% | Not published | Mean score 62.2% |
| LMArena Text | 1440 Elo | Not published | Votes 25,103 · Interval (±) ±5.0 |
| LMArena Text: coding | 1483 Elo | Not published | Votes 6,853 · Interval (±) ±7.8 |
| LMArena Text: hard prompts | 1459 Elo | Not published | Votes 16,357 · Interval (±) ±5.8 |
| LMArena Text: math | 1455 Elo | Not published | Votes 1,250 · Interval (±) ±16.7 |
| LMArena Text: instruction following | 1436 Elo | Not published | Votes 8,906 · Interval (±) ±7.1 |
| LMArena Text: creative writing | 1383 Elo | Not published | Votes 5,089 · Interval (±) ±9.2 |
| LMArena Vision | 1269 Elo | Not published | Votes 7,614 · Interval (±) ±8.2 |
| LMArena Text: English | 1448 Elo | Not published | Votes 9,398 · Interval (±) ±6.8 |
| LMArena Text: non-English | 1428 Elo | Not published | Votes 15,692 · Interval (±) ±5.9 |
| LMArena Text: Chinese | 1501 Elo | Not published | Votes 1,916 · Interval (±) ±13.8 |
| LMArena Text: German | 1443 Elo | Not published | Votes 396 · Interval (±) ±29.3 |
| LMArena Text: Japanese | 1387 Elo | Not published | Votes 461 · Interval (±) ±29.0 |
| LMArena Text: Korean | 1384 Elo | Not published | Votes 407 · Interval (±) ±29.4 |
| LMArena Text: French | 1465 Elo | Not published | Votes 869 · Interval (±) ±21.1 |
| LMArena Text: Spanish | 1449 Elo | Not published | Votes 807 · Interval (±) ±21.2 |
| LMArena Text: Russian | 1415 Elo | Not published | Votes 3,281 · Interval (±) ±10.7 |
| LMArena Text: Polish | 1439 Elo | Not published | Votes 389 · Interval (±) ±29.6 |
| LMArena Text: multi-turn | 1440 Elo | Not published | Votes 3,972 · Interval (±) ±9.9 |
| LMArena Text: longer queries | 1448 Elo | Not published | Votes 11,101 · Interval (±) ±6.8 |
| LMArena Text: expert | 1479 Elo | Not published | Votes 2,763 · Interval (±) ±11.5 |
| LMArena Text: hard prompts in English | 1461 Elo | Not published | Votes 6,237 · Interval (±) ±8.1 |
| LMArena Text: software and IT | 1478 Elo | Not published | Votes 9,805 · Interval (±) ±6.8 |
| LMArena Text: mathematical work | 1458 Elo | Not published | Votes 1,462 · Interval (±) ±15.4 |
| LMArena Text: science | 1467 Elo | Not published | Votes 4,001 · Interval (±) ±9.8 |
| LMArena Text: medicine and healthcare | 1437 Elo | Not published | Votes 1,622 · Interval (±) ±15.2 |
| LMArena Text: legal and government | 1447 Elo | Not published | Votes 1,945 · Interval (±) ±13.8 |
| LMArena Text: business and finance | 1438 Elo | Not published | Votes 4,565 · Interval (±) ±9.2 |
| LMArena Text: writing and language | 1405 Elo | Not published | Votes 6,601 · Interval (±) ±8.2 |
| LMArena Text: entertainment and media | 1393 Elo | Not published | Votes 6,213 · Interval (±) ±8.4 |
| LMArena WebDev: React | 1602 Elo | Not published | Votes 10,463 · Interval (±) ±7.5 |
| LMArena WebDev: HTML | 1570 Elo | Not published | Votes 2,462 · Interval (±) ±13.3 |
| LMArena WebDev: from an image | 1577 Elo | Not published | Votes 6,418 · Interval (±) ±8.5 |
| LMArena Vision: English | 1267 Elo | Not published | Votes 2,445 · Interval (±) ±12.9 |
| LMArena Vision: Chinese | 1326 Elo | Not published | Votes 409 · Interval (±) ±29.8 |
| LMArena Vision: reading text | 1281 Elo | Not published | Votes 5,124 · Interval (±) ±9.0 |
| LMArena Vision: diagrams | 1285 Elo | Not published | Votes 1,863 · Interval (±) ±14.2 |
| LMArena Vision: homework | 1295 Elo | Not published | Votes 919 · Interval (±) ±19.8 |
| LMArena Vision: humor | 1235 Elo | Not published | Votes 347 · Interval (±) ±32.1 |
| LMArena Vision: creative writing | 1237 Elo | Not published | Votes 696 · Interval (±) ±23.2 |