# DeepSeek V4 Pro 0423 As of October 21, 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. Page: https://llmbenchmark.ai/models/deepseek-v4-pro Data from October 21, 2026. Every figure below names the board it was read from and the day. - Maker: DeepSeek - Released: April 24, 2026 - Price per million input tokens: $0.9553 - Price per million output tokens: $1.9105 - Context window: 1.05M tokens - Overall rank: 48 of 213, by the Artificial Analysis Intelligence Index - Artificial Analysis Intelligence Index: 30.4 - Vibe Coding Index: 35.3 (from 1 of 4 coding benchmarks) Benchmark results (83 of 190): - LMArena WebDev: 1447 Elo (source: LMArena WebDev, read October 21, 2026) - GPQA Diamond: 89.4% (source: GPQA (Vals AI), read October 21, 2026) - MMLU Pro: 87.3% (source: MMLU Pro (Vals AI), read October 21, 2026) - AA Intelligence Index: 30.4 (source: Artificial Analysis (via OpenRouter), read October 21, 2026) - AA Coding Index: 59.4 (source: Artificial Analysis (via OpenRouter), read October 21, 2026) - AA Agentic Index: 26.3 (source: Artificial Analysis (via OpenRouter), read October 21, 2026) - Design Arena: websites: 1235 Elo (source: Design Arena, read October 21, 2026) - Design Arena: UI components: 1221 Elo (source: Design Arena, read October 21, 2026) - Design Arena: game dev: 1229 Elo (source: Design Arena, read October 21, 2026) - Design Arena: data viz: 1203 Elo (source: Design Arena, read October 21, 2026) - Design Arena: 3D: 1254 Elo (source: Design Arena, read October 21, 2026) - Design Arena: all code categories: 1240 Elo (source: Design Arena, read October 21, 2026) - Design Arena: SVG: 1139 Elo (source: Design Arena, read October 21, 2026) - Design Arena: ASCII art: 1148 Elo (source: Design Arena, read October 21, 2026) - Design Arena: agents building web apps: 1000 Elo (source: Design Arena, read October 21, 2026) - Design Arena: agents building full-stack apps: 948 Elo (source: Design Arena, read October 21, 2026) - Design Arena: agents building Godot games: 1059 Elo (source: Design Arena, read October 21, 2026) - LiveCodeBench (Vals AI): 87.5% (source: Vals AI boards, read October 21, 2026) - SWE-bench Verified (Vals AI): 77.4% (source: Vals AI boards, read October 21, 2026) - Terminal-Bench 4 (Vals AI): 11.1% (source: Vals AI boards, read October 21, 2026) - Vibe Code Bench (Vals AI): 49.9% (source: Vals AI boards, read October 21, 2026) - Code migration (Vals AI): 26.2% (source: Vals AI boards, read October 21, 2026) - ProgramBench (Vals AI): 0.0% (source: Vals AI boards, read October 21, 2026) - Terminal-Bench 2.1 (Vals AI): 50.2% (source: Vals AI boards, read October 21, 2026) - SkillsBench (Vals AI): 51.3% (source: Vals AI boards, read October 21, 2026) - Finance Agent (Vals AI): 44.1% (source: Vals AI boards, read October 21, 2026) - Tax Agent Bench (Vals AI): 25.2% (source: Vals AI boards, read October 21, 2026) - Legal Research Bench (Vals AI): 23.1% (source: Vals AI boards, read October 21, 2026) - Excel Modeling Benchmark (Vals AI): 51.6% (source: Vals AI boards, read October 21, 2026) - Public Benefits Bench (Vals AI): 62.9% (source: Vals AI boards, read October 21, 2026) - LegalBench (Vals AI): 80.3% (source: Vals AI boards, read October 21, 2026) - CaseLaw (Vals AI): 59.4% (source: Vals AI boards, read October 21, 2026) - CorpFin (Vals AI): 61.4% (source: Vals AI boards, read October 21, 2026) - TaxEval (Vals AI): 72.1% (source: Vals AI boards, read October 21, 2026) - MedCode (Vals AI): 40.5% (source: Vals AI boards, read October 21, 2026) - MedScribe (Vals AI): 75.1% (source: Vals AI boards, read October 21, 2026) - FrontierCode: 17.6% (source: Epoch AI benchmarking hub, read October 21, 2026) - WeirdML: 48.9% (source: Epoch AI benchmarking hub, read October 21, 2026) - GPQA Diamond (Epoch AI run): 90.9% (source: Epoch AI benchmarking hub, read October 21, 2026) - Chess puzzles: 19.0% (source: Epoch AI benchmarking hub, read October 21, 2026) - Mystery game puzzles: 17.0% (source: Epoch AI benchmarking hub, read October 21, 2026) - OTIS Mock AIME: 96.7% (source: Epoch AI benchmarking hub, read October 21, 2026) - FrontierMath, tiers 1 to 3: 45.3% (source: Epoch AI benchmarking hub, read October 21, 2026) - FrontierMath, tier 4: 2.4% (source: Epoch AI benchmarking hub, read October 21, 2026) - ProofBench: 16.0% (source: Epoch AI benchmarking hub, read October 21, 2026) - SimpleQA Verified: 47.0% (source: Epoch AI benchmarking hub, read October 21, 2026) - DTBench: 90.7% (source: Epoch AI benchmarking hub, read October 21, 2026) - LMCA: 41.2% (source: Epoch AI benchmarking hub, read October 21, 2026) - Surface Evolver Bench: 40.0% (source: Epoch AI benchmarking hub, read October 21, 2026) - CL-bench Life: 13.5% (source: Epoch AI benchmarking hub, read October 21, 2026) - ALE-Bench: 1006.1 (source: ALE-Bench (Sakana AI), read October 21, 2026) - Vending-Bench 2: $3,285 (source: Epoch AI benchmarking hub, read October 21, 2026) - Epoch Capabilities Index: 149.1 (source: Epoch AI benchmarking hub, read October 21, 2026) - LMArena Text: 1451 Elo (source: LMArena (Hugging Face dataset), read October 21, 2026) - LMArena Text: coding: 1470 Elo (source: LMArena (Hugging Face dataset), read October 21, 2026) - LMArena Text: hard prompts: 1461 Elo (source: LMArena (Hugging Face dataset), read October 21, 2026) - LMArena Text: math: 1443 Elo (source: LMArena (Hugging Face dataset), read October 21, 2026) - LMArena Text: instruction following: 1445 Elo (source: LMArena (Hugging Face dataset), read October 21, 2026) - LMArena Text: creative writing: 1446 Elo (source: LMArena (Hugging Face dataset), read October 21, 2026) - LMArena Text: English: 1459 Elo (source: LMArena (Hugging Face dataset), read October 21, 2026) - LMArena Text: non-English: 1439 Elo (source: LMArena (Hugging Face dataset), read October 21, 2026) - LMArena Text: Chinese: 1481 Elo (source: LMArena (Hugging Face dataset), read October 21, 2026) - LMArena Text: German: 1458 Elo (source: LMArena (Hugging Face dataset), read October 21, 2026) - LMArena Text: Japanese: 1446 Elo (source: LMArena (Hugging Face dataset), read October 21, 2026) - LMArena Text: Korean: 1409 Elo (source: LMArena (Hugging Face dataset), read October 21, 2026) - LMArena Text: French: 1473 Elo (source: LMArena (Hugging Face dataset), read October 21, 2026) - LMArena Text: Spanish: 1457 Elo (source: LMArena (Hugging Face dataset), read October 21, 2026) - LMArena Text: Russian: 1453 Elo (source: LMArena (Hugging Face dataset), read October 21, 2026) - LMArena Text: Polish: 1461 Elo (source: LMArena (Hugging Face dataset), read October 21, 2026) - LMArena Text: multi-turn: 1468 Elo (source: LMArena (Hugging Face dataset), read October 21, 2026) - LMArena Text: longer queries: 1458 Elo (source: LMArena (Hugging Face dataset), read October 21, 2026) - LMArena Text: expert: 1463 Elo (source: LMArena (Hugging Face dataset), read October 21, 2026) - LMArena Text: hard prompts in English: 1466 Elo (source: LMArena (Hugging Face dataset), read October 21, 2026) - LMArena Text: software and IT: 1469 Elo (source: LMArena (Hugging Face dataset), read October 21, 2026) - LMArena Text: mathematical work: 1455 Elo (source: LMArena (Hugging Face dataset), read October 21, 2026) - LMArena Text: science: 1470 Elo (source: LMArena (Hugging Face dataset), read October 21, 2026) - LMArena Text: medicine and healthcare: 1466 Elo (source: LMArena (Hugging Face dataset), read October 21, 2026) - LMArena Text: legal and government: 1464 Elo (source: LMArena (Hugging Face dataset), read October 21, 2026) - LMArena Text: business and finance: 1443 Elo (source: LMArena (Hugging Face dataset), read October 21, 2026) - LMArena Text: writing and language: 1447 Elo (source: LMArena (Hugging Face dataset), read October 21, 2026) - LMArena Text: entertainment and media: 1431 Elo (source: LMArena (Hugging Face dataset), read October 21, 2026) - LMArena WebDev: React: 1441 Elo (source: LMArena (Hugging Face dataset), read October 21, 2026) - LMArena WebDev: HTML: 1435 Elo (source: LMArena (Hugging Face dataset), read October 21, 2026)