As of October 20, 2026, DeepSeek V4.1 Flash ranks #73 of 213 models overall with 24.7 on the Artificial Analysis Intelligence Index. Its strongest category is web design, where it ranks #14 of 131. DeepSeek V4.1 Flash costs $0.0352 per million input tokens and $0.0112 per million output tokens. It was released on September 10, 2026.
Its output price ranks 6 of 349 priced models, counting from the cheapest.
DeepSeek V4.1 Flash is a sparse mixture-of-experts model from DeepSeek, and the first built on the company's Causal Encoder-Decoder (CED) architecture. It activates 8B parameters on input and 16B on...
deepseek/deepseek-v4.1-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 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, AA Coding Index, LiveCodeBench (Vals AI), SWE-bench Verified (Vals AI), LiveCodeBench (Artificial Analysis run), Terminal-Bench Hard (Artificial Analysis run), Terminal-Bench, DeepSWE, FrontierSWE, GSO-Bench, WeirdML, MirrorCode, Cybench, LMArena Text: coding, LMArena Text: software and IT
Not measured on AA Agentic Index, 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, BALROG, DeepResearch Bench, PostTrainBench, TheAgentCompany, OSWorld, SpireClimb, Vending-Bench 2, LMArena Search
Not measured on GPQA Diamond, MMMU Pro (Vals AI), GPQA Diamond (Artificial Analysis run), Humanity's Last Exam, SimpleBench, EBR-bench, VPCT, BIG-Bench Hard, LMArena Text: hard prompts, LMArena Text: expert, LMArena Text: hard prompts in English
Not measured on AIME, MATH 500 (Vals AI), MGSM (Vals AI), AA Math Index, AIME 2025 (Artificial Analysis run), MATH level 5, GSM8K, LMArena Text: math, LMArena Text: mathematical work
Not measured on MMLU Pro, CaseLaw (Vals AI), CorpFin (Vals AI), TaxEval (Vals AI), MortgageTax (Vals AI), MedQA (Vals AI), MMLU Pro (Artificial Analysis run), MMLU, GeoBench, AI2 Reasoning Challenge, LMArena Text: science, LMArena Text: medicine and healthcare, LMArena Text: legal and government, LMArena Text: business and finance
Not measured on Vals Index, Vals Multimodal Index, IFBench, Fiction.LiveBench, Creative writing (Lech Mazur), CL-bench, ExploitBench, HellaSwag, WinoGrande, PIQA, CL-bench Life, LMArena Text, LMArena Text: instruction following, LMArena Text: creative writing, LMArena Text: English, LMArena Text: non-English, LMArena Text: Chinese, LMArena Text: German, LMArena Text: Japanese, LMArena Text: Korean, LMArena Text: French, LMArena Text: Spanish, LMArena Text: Russian, LMArena Text: Polish, LMArena Text: multi-turn, LMArena Text: longer queries, LMArena Text: writing and language, LMArena Text: entertainment and media, 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 | 90.2% | 20% |
| LMArena WebDevCoding | 1618 | 15% |
| Vals IndexGeneral | Not measured | Not in index |
| GPQA DiamondReasoning | Not measured | Not in index |
| AIMEMath | Not measured | Not in index |
| MMLU ProKnowledge | Not measured | Not in index |
| AA Intelligence IndexIntelligence | 24.7 | Not in index |
| AA Coding IndexCoding | Not measured | Not in index |
| AA Agentic IndexAgentic work | Not measured | Not in index |
| Design Arena: websitesWeb design | 1309 | Not in index |
| Design Arena: UI componentsWeb design | 1315 | Not in index |
| Design Arena: game devWeb design | 1331 | Not in index |
| Design Arena: data vizWeb design | 1291 | Not in index |
| Design Arena: 3DWeb design | 1356 | Not in index |
| Design Arena: all code categoriesWeb design | 1321 | Not in index |
| Design Arena: SVGWeb design | 1243 | Not in index |
| Design Arena: ASCII artWeb design | 1265 | 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 | 86.7% | Not in index |
| LiveBench data analysisGeneral | 79.3% | Not in index |
| LiveBench researchAgentic work | 86.8% | Not in index |
| LiveBench browserAgentic work | 84.0% | Not in index |
| LiveBench long agenticAgentic work | 40.1% | Not in index |
| LiveBench designWeb design | 79.2% | Not in index |
| LiveCodeBench (Vals AI)Coding | Not measured | Not in index |
| SWE-bench Verified (Vals AI)Coding | Not measured | Not in index |
| Terminal-Bench 4 (Vals AI)Coding | 19.7% | Not in index |
| Vibe Code Bench (Vals AI)Coding | 84.7% | Not in index |
| Code migration (Vals AI)Coding | 45.6% | Not in index |
| ProgramBench (Vals AI)Coding | 0.5% | Not in index |
| SREBench (Vals AI)Agentic work | 0.8% | Not in index |
| IOI (Vals AI)Coding | 40.3% | Not in index |
| Terminal-Bench 2.1 (Vals AI)Coding | 74.5% | Not in index |
| SWE-bench Multimodal (Vals AI)Coding | 46.5% | Not in index |
| Vibe Code Bench 1-100 (Vals AI)Coding | 16.4% | Not in index |
| SkillsBench (Vals AI)Coding | 69.8% | Not in index |
| CyberBench (Vals AI)Coding | 73.7% | Not in index |
| Finance Agent (Vals AI)Agentic work | 53.5% | Not in index |
| Tax Agent Bench (Vals AI)Agentic work | 26.6% | Not in index |
| Legal Research Bench (Vals AI)Agentic work | 41.4% | Not in index |
| Harvey's Legal Agent Benchmark (Vals AI)Agentic work | Not measured | Not in index |
| Excel Modeling Benchmark (Vals AI)Agentic work | 57.2% | Not in index |
| BioMysteryBench (Vals AI)Agentic work | 67.8% | Not in index |
| Terminal-Bench-Science (Vals AI)Agentic work | 0.0% | Not in index |
| Vals Science IndexAgentic work | 29.6% | 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 | 64.3% | Not in index |
| MysteryMechanism (Vals AI)Reasoning | 21.2% | Not in index |
| MMMU Pro (Vals AI)Reasoning | Not measured | 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 | 47.9% | Not in index |
| LegalBench (Vals AI)Knowledge | 83.3% | 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 | Not measured | Not in index |
| MortgageTax (Vals AI)Knowledge | Not measured | Not in index |
| MedQA (Vals AI)Knowledge | Not measured | Not in index |
| MedCode (Vals AI)Knowledge | 41.2% | Not in index |
| MedScribe (Vals AI)General | 85.5% | 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 | Not measured | Not in index |
| Humanity's Last Exam (Artificial Analysis run)Reasoning | 39.2% | 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 | 51.9% | 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 | Not measured | Not in index |
| FrontierCodeCoding | 43.9% | 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 | 39.5% | 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 | 89.8% | Not in index |
| ARC-AGIReasoning | 94.5% | Not in index |
| ARC-AGI-2Reasoning | 72.9% | Not in index |
| Humanity's Last ExamReasoning | Not measured | Not in index |
| SimpleBenchReasoning | Not measured | Not in index |
| Chess puzzlesReasoning | 48.0% | Not in index |
| Mystery game puzzlesReasoning | 43.0% | Not in index |
| EBR-benchReasoning | Not measured | Not in index |
| OTIS Mock AIMEMath | 98.3% | Not in index |
| FrontierMath, tiers 1 to 3Math | 67.4% | Not in index |
| FrontierMath, tier 4Math | 26.8% | Not in index |
| ProofBenchMath | 54.0% | Not in index |
| MATH level 5Math | Not measured | Not in index |
| GSM8KMath | Not measured | Not in index |
| SimpleQA VerifiedKnowledge | 42.9% | Not in index |
| MMLUKnowledge | Not measured | Not in index |
| GeoBenchKnowledge | Not measured | Not in index |
| DTBenchGeneral | 89.9% | Not in index |
| LMCAGeneral | 47.0% | 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 | 46.3% | Not in index |
| Furniture assemblyGeneral | 34.2% | 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 | 1092.3 | Not in index |
| Vending-Bench 2Agentic work | Not measured | Not in index |
| Epoch Capabilities IndexIntelligence | 155.6 | Not in index |
| LMArena TextGeneral | Not measured | Not in index |
| LMArena Text: codingCoding | Not measured | Not in index |
| LMArena Text: hard promptsReasoning | Not measured | Not in index |
| LMArena Text: mathMath | Not measured | Not in index |
| LMArena Text: instruction followingGeneral | Not measured | Not in index |
| LMArena Text: creative writingGeneral | Not measured | Not in index |
| LMArena VisionGeneral | 1278 | Not in index |
| LMArena Text: EnglishGeneral | Not measured | Not in index |
| LMArena Text: non-EnglishGeneral | Not measured | Not in index |
| LMArena Text: ChineseGeneral | Not measured | Not in index |
| LMArena Text: GermanGeneral | Not measured | Not in index |
| LMArena Text: JapaneseGeneral | Not measured | Not in index |
| LMArena Text: KoreanGeneral | Not measured | Not in index |
| LMArena Text: FrenchGeneral | Not measured | Not in index |
| LMArena Text: SpanishGeneral | Not measured | Not in index |
| LMArena Text: RussianGeneral | Not measured | Not in index |
| LMArena Text: PolishGeneral | Not measured | Not in index |
| LMArena Text: multi-turnGeneral | Not measured | Not in index |
| LMArena Text: longer queriesGeneral | Not measured | Not in index |
| LMArena Text: expertReasoning | Not measured | Not in index |
| LMArena Text: hard prompts in EnglishReasoning | Not measured | Not in index |
| LMArena Text: software and ITCoding | Not measured | Not in index |
| LMArena Text: mathematical workMath | Not measured | Not in index |
| LMArena Text: scienceKnowledge | Not measured | Not in index |
| LMArena Text: medicine and healthcareKnowledge | Not measured | Not in index |
| LMArena Text: legal and governmentKnowledge | Not measured | Not in index |
| LMArena Text: business and financeKnowledge | Not measured | Not in index |
| LMArena Text: writing and languageGeneral | Not measured | Not in index |
| LMArena Text: entertainment and mediaGeneral | Not measured | Not in index |
| LMArena WebDev: ReactCoding | 1628 | Not in index |
| LMArena WebDev: HTMLCoding | 1612 | Not in index |
| LMArena WebDev: from an imageCoding | 1606 | Not in index |
| LMArena Vision: EnglishGeneral | 1288 | Not in index |
| LMArena Vision: ChineseGeneral | 1327 | Not in index |
| LMArena Vision: reading textGeneral | 1282 | Not in index |
| LMArena Vision: diagramsReasoning | 1297 | Not in index |
| LMArena Vision: homeworkReasoning | 1307 | Not in index |
| LMArena Vision: humorGeneral | 1260 | Not in index |
| LMArena Vision: captioningGeneral | Not measured | Not in index |
| LMArena Vision: recognizing thingsGeneral | Not measured | Not in index |
| LMArena Vision: creative writingGeneral | 1275 | 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.
Neither board that publishes what a SWE-bench Verified attempt costs, Vals AI and swebench.com, has run this model. We leave the number out rather than estimate it.
LiveBench, on its own coding tasks, publishes what one task cost this model: $0.238, at a score of 90.2%. LiveBench counts that as $0.264 per successful task. Different tasks from SWE-bench, so it is not our number and does not enter its ranking. LiveBench coding
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 | 90.2% | $0.2377 per task | Output tokens per task 73,074 |
| LiveBench reasoning | 86.7% | $0.0457 per task | Output tokens per task 37,763 |
| LiveBench data analysis | 79.3% | $0.0711 per task | Output tokens per task 58,326 |
| LiveBench research | 86.8% | $0.4087 per task | Output tokens per task 142,711 |
| LiveBench browser | 84.0% | $0.3486 per task | Output tokens per task 42,493 |
| LiveBench long agentic | 40.1% | $1.7415 per task | Output tokens per task 451,375 |
| LiveBench design | 79.2% | $0.1748 per task | Output tokens per task 90,915 |
| Terminal-Bench 4 (Vals AI) | 19.7% | $0.50 per test | Duration, as printed 48m 22s |
| Vibe Code Bench (Vals AI) | 84.7% | $0.41 per test | Duration, as printed 15m 28s |
| Code migration (Vals AI) | 45.6% | $0.94 per test | Duration, as printed 1h 45m |
| ProgramBench (Vals AI) | 0.5% | $0.90 per test | Duration, as printed 1h 02m |
| SREBench (Vals AI) | 0.8% | $0.55 per test | Duration, as printed 1h 01m |
| IOI (Vals AI) | 40.3% | $0.24 per test | Duration, as printed 18m 30s |
|---|---|---|---|
| Terminal-Bench 2.1 (Vals AI) | 74.5% | $0.10 per test | Duration, as printed 10m 05s |
| SWE-bench Multimodal (Vals AI) | 46.5% | $0.23 per test | Duration, as printed 19m 24s |
| Vibe Code Bench 1-100 (Vals AI) | 16.4% | $0.69 per test | Duration, as printed 28m 21s |
| SkillsBench (Vals AI) | 69.8% | $0.09 per test | Duration, as printed 3m 43s |
| CyberBench (Vals AI) | 73.7% | $0.07 per test | Duration, as printed 13m 50s |
| Finance Agent (Vals AI) | 53.5% | $0.21 per test | Duration, as printed 6m 04s |
| Tax Agent Bench (Vals AI) | 26.6% | $0.13 per test | Duration, as printed 5m 49s |
| Legal Research Bench (Vals AI) | 41.4% | $0.25 per test | Duration, as printed 11m 42s |
| Excel Modeling Benchmark (Vals AI) | 57.2% | $0.23 per test | Duration, as printed 13m 00s |
| BioMysteryBench (Vals AI) | 67.8% | $0.23 per test | Duration, as printed 14m 50s |
| Terminal-Bench-Science (Vals AI) | 0.0% | $0.47 per test | Duration, as printed 2h 57m |
| Vals Science Index | 29.6% | $0.29 per test | Duration, as printed 1h 07m |
| Public Benefits Bench (Vals AI) | 64.3% | $0.07 per test | Nothing else |
| MysteryMechanism (Vals AI) | 21.2% | $0.16 per test | Duration, as printed 8m 04s |
| ProofBench | 54.0% | $0.1264 per test | Time per proof 9m 07s |
| Surface Evolver Bench | 46.3% | $2.1277 of the run | Pass rate 31.3% · Tokens for the run 3.3M |
| ALE-Bench | 1092.3 | $0.0817 per problem | Tokens per problem 70,295 |
| LMArena WebDev | 1618 Elo | Not published | Votes 3,528 · Interval (±) ±11.0 |
| Design Arena: websites | 1309 Elo | Not published | Battles 26,282 |
| Design Arena: UI components | 1315 Elo | Not published | Battles 1,202 |
| Design Arena: game dev | 1331 Elo | Not published | Battles 12,254 |
| Design Arena: data viz | 1291 Elo | Not published | Battles 985 |
| Design Arena: 3D | 1356 Elo | Not published | Battles 5,313 |
| Design Arena: all code categories | 1321 Elo | Not published | Battles 42,160 |
| Design Arena: SVG | 1243 Elo | Not published | Battles 1,010 |
| Design Arena: ASCII art | 1265 Elo | Not published | Battles 288 |
| SAGE (Vals AI) | 47.9% | Not published | Latency, as printed 36 s |
| LegalBench (Vals AI) | 83.3% | Not published | Latency, as printed 6.5 s |
| MedCode (Vals AI) | 41.2% | Not published | Latency, as printed 35 s |
| MedScribe (Vals AI) | 85.5% | Not published | Latency, as printed 54 s |
| APEX-Agents | 39.5% | Not published | Mean score 50.5% |
| LMArena Vision | 1278 Elo | Not published | Votes 4,100 · Interval (±) ±10.2 |
| LMArena WebDev: React | 1628 Elo | Not published | Votes 2,162 · Interval (±) ±14.0 |
| LMArena WebDev: HTML | 1612 Elo | Not published | Votes 608 · Interval (±) ±26.2 |
| LMArena WebDev: from an image | 1606 Elo | Not published | Votes 767 · Interval (±) ±22.2 |
| LMArena Vision: English | 1288 Elo | Not published | Votes 1,301 · Interval (±) ±17.3 |
| LMArena Vision: Chinese | 1327 Elo | Not published | Votes 199 · Interval (±) ±41.5 |
| LMArena Vision: reading text | 1282 Elo | Not published | Votes 2,786 · Interval (±) ±11.8 |
| LMArena Vision: diagrams | 1297 Elo | Not published | Votes 1,085 · Interval (±) ±18.6 |
| LMArena Vision: homework | 1307 Elo | Not published | Votes 521 · Interval (±) ±25.5 |
| LMArena Vision: humor | 1260 Elo | Not published | Votes 166 · Interval (±) ±45.5 |
| LMArena Vision: creative writing | 1275 Elo | Not published | Votes 345 · Interval (±) ±32.9 |