As of October 20, 2026, DeepSeek V4 Pro 0423 ranks #48 of 213 models overall with 30.4 on the Artificial Analysis Intelligence Index. Its strongest category is knowledge, where it ranks #30 of 147. DeepSeek V4 Pro 0423 costs $0.9553 per million input tokens and $1.9105 per million output tokens. It was released on April 24, 2026.
Its output price ranks 182 of 349 priced models, counting from the cheapest.
DeepSeek V4 Pro is a large-scale Mixture-of-Experts model from DeepSeek with 1.6T total parameters and 49B activated parameters, supporting a 1M-token context window. It is designed for advanced reasoning, coding,...
deepseek/deepseek-v4-pro 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, IOI (Vals AI), SWE-bench Multimodal (Vals AI), Vibe Code Bench 1-100 (Vals AI), CyberBench (Vals AI), LiveCodeBench (Artificial Analysis run), SciCode, Terminal-Bench Hard (Artificial Analysis run), Terminal-Bench, DeepSWE, FrontierSWE, GSO-Bench, MirrorCode, Cybench, LMArena WebDev: from an image
Not measured on Design Arena: agents building mobile apps, Design Arena: agents building Android apps, Design Arena: agents building games, Design Arena: HTML slides, Design Arena: PowerPoint slides, Design Arena: spreadsheets, LiveBench research, LiveBench browser, LiveBench long agentic, SREBench (Vals AI), Harvey's Legal Agent Benchmark (Vals AI), BioMysteryBench (Vals AI), Terminal-Bench-Science (Vals AI), Vals Science Index, Time Horizon Index (Vals AI), CUA-bench (Vals AI), Robo-bench (Vals AI), τ²-Bench Telecom, APEX-Agents, METR time horizons, Remote Labor Index, GDPval, OSWorld 2.0, BALROG, DeepResearch Bench, PostTrainBench, TheAgentCompany, OSWorld, SpireClimb, LMArena Search
Not measured on LiveBench reasoning, MysteryMechanism (Vals AI), MMMU Pro (Vals AI), GPQA Diamond (Artificial Analysis run), Humanity's Last Exam (Artificial Analysis run), ARC-AGI, ARC-AGI-2, Humanity's Last Exam, SimpleBench, EBR-bench, VPCT, BIG-Bench Hard, LMArena Vision: diagrams, LMArena Vision: homework
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 MortgageTax (Vals AI), MedQA (Vals AI), MMLU Pro (Artificial Analysis run), MMLU, GeoBench, AI2 Reasoning Challenge
Not measured on LiveBench design
Not measured on Vals Index, LiveBench data analysis, SAGE (Vals AI), Vals Multimodal Index, IFBench, Long context reasoning (AA-LCR), Fiction.LiveBench, Creative writing (Lech Mazur), CL-bench, Furniture assembly, ExploitBench, HellaSwag, WinoGrande, PIQA, LMArena Vision, LMArena Vision: English, LMArena Vision: Chinese, LMArena Vision: reading text, LMArena Vision: humor, LMArena Vision: captioning, LMArena Vision: recognizing things, LMArena Vision: creative writing, 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 | Not measured | 20% |
| LMArena WebDevCoding | 1447 | 15% |
| Vals IndexGeneral | Not measured | Not in index |
| GPQA DiamondReasoning | 89.4% | Not in index |
| AIMEMath | Not measured | Not in index |
| MMLU ProKnowledge | 87.3% | Not in index |
| AA Intelligence IndexIntelligence | 30.4 | Not in index |
| AA Coding IndexCoding | 59.4 | Not in index |
| AA Agentic IndexAgentic work | 26.3 | Not in index |
| Design Arena: websitesWeb design | 1235 | Not in index |
| Design Arena: UI componentsWeb design | 1222 | Not in index |
| Design Arena: game devWeb design | 1229 | Not in index |
| Design Arena: data vizWeb design | 1203 | Not in index |
| Design Arena: 3DWeb design | 1254 | Not in index |
| Design Arena: all code categoriesWeb design | 1241 | Not in index |
| Design Arena: SVGWeb design | 1139 | Not in index |
| Design Arena: ASCII artWeb design | 1149 | Not in index |
| Design Arena: agents building web appsAgentic work | 1000 | Not in index |
| Design Arena: agents building full-stack appsAgentic work | 948 | 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 | 1059 | 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 | 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 | 87.5% | Not in index |
| SWE-bench Verified (Vals AI)Coding | 77.4% | Not in index |
| Terminal-Bench 4 (Vals AI)Coding | 11.1% | Not in index |
| Vibe Code Bench (Vals AI)Coding | 49.9% | Not in index |
| Code migration (Vals AI)Coding | 26.2% | 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 | Not measured | Not in index |
| Terminal-Bench 2.1 (Vals AI)Coding | 50.2% | 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 | 51.3% | Not in index |
| CyberBench (Vals AI)Coding | Not measured | Not in index |
| Finance Agent (Vals AI)Agentic work | 44.1% | Not in index |
| Tax Agent Bench (Vals AI)Agentic work | 25.2% | Not in index |
| Legal Research Bench (Vals AI)Agentic work | 23.1% | Not in index |
| Harvey's Legal Agent Benchmark (Vals AI)Agentic work | Not measured | Not in index |
| Excel Modeling Benchmark (Vals AI)Agentic work | 51.6% | Not in index |
| BioMysteryBench (Vals AI)Agentic work | Not measured | Not in index |
| Terminal-Bench-Science (Vals AI)Agentic work | Not measured | 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 | 62.9% | Not in index |
| MysteryMechanism (Vals AI)Reasoning | Not measured | 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 | Not measured | Not in index |
| LegalBench (Vals AI)Knowledge | 80.3% | Not in index |
| CaseLaw (Vals AI)Knowledge | 59.4% | Not in index |
| CorpFin (Vals AI)Knowledge | 61.4% | Not in index |
| TaxEval (Vals AI)Knowledge | 72.1% | 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 | 40.5% | Not in index |
| MedScribe (Vals AI)General | 75.1% | 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 | Not measured | 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 | Not measured | 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 | Not measured | 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 | 17.6% | Not in index |
| FrontierSWECoding | Not measured | Not in index |
| GSO-BenchCoding | Not measured | Not in index |
| WeirdMLCoding | 48.9% | Not in index |
| MirrorCodeCoding | Not measured | Not in index |
| APEX-AgentsAgentic work | Not measured | 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 | 90.9% | Not in index |
| ARC-AGIReasoning | Not measured | Not in index |
| ARC-AGI-2Reasoning | Not measured | Not in index |
| Humanity's Last ExamReasoning | Not measured | Not in index |
| SimpleBenchReasoning | Not measured | Not in index |
| Chess puzzlesReasoning | 19.0% | Not in index |
| Mystery game puzzlesReasoning | 17.0% | Not in index |
| EBR-benchReasoning | Not measured | Not in index |
| OTIS Mock AIMEMath | 96.7% | Not in index |
| FrontierMath, tiers 1 to 3Math | 45.3% | Not in index |
| FrontierMath, tier 4Math | 2.4% | 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 | 47.0% | Not in index |
| MMLUKnowledge | Not measured | Not in index |
| GeoBenchKnowledge | Not measured | Not in index |
| DTBenchGeneral | 90.7% | Not in index |
| LMCAGeneral | 41.2% | 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 | 40.0% | 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 | 13.5% | Not in index |
| ALE-BenchCoding | 1006.1 | Not in index |
| Vending-Bench 2Agentic work | $3,285 | Not in index |
| Epoch Capabilities IndexIntelligence | 149.2 | Not in index |
| LMArena TextGeneral | 1451 | Not in index |
| LMArena Text: codingCoding | 1469 | Not in index |
| LMArena Text: hard promptsReasoning | 1461 | Not in index |
| LMArena Text: mathMath | 1443 | Not in index |
| LMArena Text: instruction followingGeneral | 1445 | Not in index |
| LMArena Text: creative writingGeneral | 1446 | Not in index |
| LMArena VisionGeneral | Not measured | Not in index |
| LMArena Text: EnglishGeneral | 1459 | Not in index |
| LMArena Text: non-EnglishGeneral | 1439 | Not in index |
| LMArena Text: ChineseGeneral | 1481 | Not in index |
| LMArena Text: GermanGeneral | 1458 | Not in index |
| LMArena Text: JapaneseGeneral | 1446 | Not in index |
| LMArena Text: KoreanGeneral | 1409 | Not in index |
| LMArena Text: FrenchGeneral | 1473 | Not in index |
| LMArena Text: SpanishGeneral | 1456 | Not in index |
| LMArena Text: RussianGeneral | 1452 | Not in index |
| LMArena Text: PolishGeneral | 1461 | Not in index |
| LMArena Text: multi-turnGeneral | 1467 | Not in index |
| LMArena Text: longer queriesGeneral | 1457 | Not in index |
| LMArena Text: expertReasoning | 1463 | Not in index |
| LMArena Text: hard prompts in EnglishReasoning | 1466 | Not in index |
| LMArena Text: software and ITCoding | 1469 | Not in index |
| LMArena Text: mathematical workMath | 1455 | Not in index |
| LMArena Text: scienceKnowledge | 1470 | Not in index |
| LMArena Text: medicine and healthcareKnowledge | 1466 | Not in index |
| LMArena Text: legal and governmentKnowledge | 1464 | Not in index |
| LMArena Text: business and financeKnowledge | 1443 | Not in index |
| LMArena Text: writing and languageGeneral | 1447 | Not in index |
| LMArena Text: entertainment and mediaGeneral | 1430 | Not in index |
| LMArena WebDev: ReactCoding | 1441 | Not in index |
| LMArena WebDev: HTMLCoding | 1435 | Not in index |
| LMArena WebDev: from an imageCoding | Not measured | Not in index |
| LMArena Vision: EnglishGeneral | Not measured | Not in index |
| LMArena Vision: ChineseGeneral | Not measured | Not in index |
| LMArena Vision: reading textGeneral | Not measured | Not in index |
| LMArena Vision: diagramsReasoning | Not measured | Not in index |
| LMArena Vision: homeworkReasoning | Not measured | Not in index |
| LMArena Vision: humorGeneral | Not measured | Not in index |
| LMArena Vision: captioningGeneral | Not measured | Not in index |
| LMArena Vision: recognizing thingsGeneral | Not measured | Not in index |
| LMArena Vision: creative writingGeneral | Not measured | 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 |
|---|---|---|---|
| SWE-bench Verified (Vals AI) | 77.4% | $0.44 per test | Duration, as printed 10m 35s |
| Terminal-Bench 4 (Vals AI) | 11.1% | $3.45 per test | Duration, as printed 1h 26m |
| Vibe Code Bench (Vals AI) | 49.9% | $2.21 per test | Duration, as printed 56m 59s |
| Code migration (Vals AI) | 26.2% | $1.07 per test | Duration, as printed 28m 58s |
| Terminal-Bench 2.1 (Vals AI) | 50.2% | $0.24 per test | Duration, as printed 17m 58s |
| SkillsBench (Vals AI) | 51.3% | $0.40 per test | Duration, as printed 8m 16s |
| Finance Agent (Vals AI) | 44.1% | $0.88 per test | Duration, as printed 25m 26s |
| Tax Agent Bench (Vals AI) | 25.2% | $0.72 per test | Duration, as printed 20m 45s |
| Legal Research Bench (Vals AI) | 23.1% | $0.68 per test | Duration, as printed 17m 05s |
| Excel Modeling Benchmark (Vals AI) | 51.6% | $0.80 per test | Duration, as printed 13m 42s |
| Public Benefits Bench (Vals AI) | 62.9% | $0.46 per test | Nothing else |
| WeirdML | 48.9% | $0.3403 per run | Median lines of code 272 |
| ProofBench | 16.0% | $0.0336 per test | Time per proof 7m 03s |
|---|---|---|---|
| Surface Evolver Bench | 40.0% | $3.857 of the run | Pass rate 25.0% · Tokens for the run 4.5M |
| ALE-Bench | 1006.1 | $0.1481 per problem | Tokens per problem 45,318 |
| LMArena WebDev | 1447 Elo | Not published | Votes 13,979 · Interval (±) ±6.3 |
| GPQA Diamond | 89.4% | Not published | Latency, as printed 15m 00s |
| MMLU Pro | 87.3% | Not published | Latency, as printed 9m 38s |
| Design Arena: websites | 1235 Elo | Not published | Battles 15,533 |
| Design Arena: UI components | 1222 Elo | Not published | Battles 2,145 |
| Design Arena: game dev | 1229 Elo | Not published | Battles 4,413 |
| Design Arena: data viz | 1203 Elo | Not published | Battles 1,172 |
| Design Arena: 3D | 1254 Elo | Not published | Battles 4,513 |
| Design Arena: all code categories | 1241 Elo | Not published | Battles 27,276 |
| Design Arena: SVG | 1139 Elo | Not published | Battles 2,058 |
| Design Arena: ASCII art | 1149 Elo | Not published | Battles 679 |
| LiveCodeBench (Vals AI) | 87.5% | Not published | Latency, as printed 11m 56s |
| ProgramBench (Vals AI) | 0.0% | Not published | Duration, as printed 1h 03m |
| LegalBench (Vals AI) | 80.3% | Not published | Latency, as printed 3m 04s |
| CaseLaw (Vals AI) | 59.4% | Not published | Latency, as printed 48 s |
| CorpFin (Vals AI) | 61.4% | Not published | Latency, as printed 1m 19s |
| TaxEval (Vals AI) | 72.1% | Not published | Latency, as printed 3m 10s |
| MedCode (Vals AI) | 40.5% | Not published | Latency, as printed 6m 23s |
| MedScribe (Vals AI) | 75.1% | Not published | Latency, as printed 5m 46s |
| LMArena Text | 1451 Elo | Not published | Votes 57,594 · Interval (±) ±3.9 |
| LMArena Text: coding | 1469 Elo | Not published | Votes 17,136 · Interval (±) ±5.9 |
| LMArena Text: hard prompts | 1461 Elo | Not published | Votes 38,511 · Interval (±) ±4.6 |
| LMArena Text: math | 1443 Elo | Not published | Votes 3,063 · Interval (±) ±11.1 |
| LMArena Text: instruction following | 1445 Elo | Not published | Votes 20,027 · Interval (±) ±5.6 |
| LMArena Text: creative writing | 1446 Elo | Not published | Votes 9,726 · Interval (±) ±7.2 |
| LMArena Text: English | 1459 Elo | Not published | Votes 25,292 · Interval (±) ±5.1 |
| LMArena Text: non-English | 1439 Elo | Not published | Votes 32,302 · Interval (±) ±4.7 |
| LMArena Text: Chinese | 1481 Elo | Not published | Votes 3,389 · Interval (±) ±10.7 |
| LMArena Text: German | 1458 Elo | Not published | Votes 997 · Interval (±) ±19.3 |
| LMArena Text: Japanese | 1446 Elo | Not published | Votes 722 · Interval (±) ±23.5 |
| LMArena Text: Korean | 1409 Elo | Not published | Votes 1,111 · Interval (±) ±18.8 |
| LMArena Text: French | 1473 Elo | Not published | Votes 2,211 · Interval (±) ±14.5 |
| LMArena Text: Spanish | 1456 Elo | Not published | Votes 1,731 · Interval (±) ±15.2 |
| LMArena Text: Russian | 1452 Elo | Not published | Votes 6,319 · Interval (±) ±8.2 |
| LMArena Text: Polish | 1461 Elo | Not published | Votes 1,124 · Interval (±) ±17.9 |
| LMArena Text: multi-turn | 1467 Elo | Not published | Votes 10,357 · Interval (±) ±7.0 |
| LMArena Text: longer queries | 1457 Elo | Not published | Votes 25,932 · Interval (±) ±5.3 |
| LMArena Text: expert | 1463 Elo | Not published | Votes 5,913 · Interval (±) ±8.4 |
| LMArena Text: hard prompts in English | 1466 Elo | Not published | Votes 17,840 · Interval (±) ±5.8 |
| LMArena Text: software and IT | 1469 Elo | Not published | Votes 23,637 · Interval (±) ±5.2 |
| LMArena Text: mathematical work | 1455 Elo | Not published | Votes 3,288 · Interval (±) ±10.9 |
| LMArena Text: science | 1470 Elo | Not published | Votes 9,166 · Interval (±) ±7.1 |
| LMArena Text: medicine and healthcare | 1466 Elo | Not published | Votes 4,066 · Interval (±) ±10.0 |
| LMArena Text: legal and government | 1464 Elo | Not published | Votes 4,494 · Interval (±) ±9.5 |
| LMArena Text: business and finance | 1443 Elo | Not published | Votes 11,386 · Interval (±) ±6.7 |
| LMArena Text: writing and language | 1447 Elo | Not published | Votes 14,140 · Interval (±) ±6.3 |
| LMArena Text: entertainment and media | 1430 Elo | Not published | Votes 12,801 · Interval (±) ±6.5 |
| LMArena WebDev: React | 1441 Elo | Not published | Votes 9,622 · Interval (±) ±7.1 |
| LMArena WebDev: HTML | 1435 Elo | Not published | Votes 1,502 · Interval (±) ±15.9 |