# SpaceXAI Grok 4.6 As of October 21, 2026, SpaceXAI Grok 4.6 ranks #24 of 123 models overall with 67.4 ±6.1 on the LLMBenchmark Index. Grok 4.6 ranks #20 of 122 in reasoning, its strongest category. SpaceXAI Grok 4.6 costs $2.00 per million input tokens and $6.00 per million output tokens. Grok 4.6 was released on August 12, 2026. Page: https://llmbenchmark.ai/models/grok-4-6 Data from October 21, 2026. Every figure below names the board it was read from and the day. - Maker: xAI - Released: August 12, 2026 - Price per million input tokens: $2.00 - Price per million output tokens: $6.00 - Context window: 500K tokens - Overall rank: 24 of 123, by the LLMBenchmark Index - LLMBenchmark Index: 67.4 ±6.1 (90% margin, from 7 of 7 inputs) - Artificial Analysis Intelligence Index: 44.3 - Vibe Coding Index: 65.7 (from 6 of 6 coding benchmarks) Benchmark results (123 of 195): - LiveBench coding: 89.1% (source: LiveBench, read October 21, 2026) - LMArena WebDev: 1617 Elo (source: LMArena WebDev, read October 21, 2026) - GPQA Diamond: 94.7% (source: GPQA (Vals AI), read October 21, 2026) - MMLU Pro: 89.4% (source: MMLU Pro (Vals AI), read October 21, 2026) - AA Intelligence Index: 44.3 (source: Artificial Analysis (via OpenRouter), read October 21, 2026) - AA Coding Index: 76.8 (source: Artificial Analysis (via OpenRouter), read October 21, 2026) - AA Agentic Index: 53.0 (source: Artificial Analysis (via OpenRouter), read October 21, 2026) - Design Arena: websites: 1289 Elo (source: Design Arena, read October 21, 2026) - Design Arena: UI components: 1295 Elo (source: Design Arena, read October 21, 2026) - Design Arena: game dev: 1296 Elo (source: Design Arena, read October 21, 2026) - Design Arena: data viz: 1282 Elo (source: Design Arena, read October 21, 2026) - Design Arena: 3D: 1277 Elo (source: Design Arena, read October 21, 2026) - Design Arena: all code categories: 1292 Elo (source: Design Arena, read October 21, 2026) - Design Arena: SVG: 1239 Elo (source: Design Arena, read October 21, 2026) - Design Arena: ASCII art: 1278 Elo (source: Design Arena, read October 21, 2026) - Design Arena: agents building web apps: 1248 Elo (source: Design Arena, read October 21, 2026) - Design Arena: agents building full-stack apps: 1264 Elo (source: Design Arena, read October 21, 2026) - Design Arena: agents building mobile apps: 1236 Elo (source: Design Arena, read October 21, 2026) - Design Arena: agents building Android apps: 1297 Elo (source: Design Arena, read October 21, 2026) - Design Arena: agents building Godot games: 1276 Elo (source: Design Arena, read October 21, 2026) - Design Arena: agents building games: 1208 Elo (source: Design Arena, read October 21, 2026) - Design Arena: HTML slides: 1249 Elo (source: Design Arena, read October 21, 2026) - Design Arena: PowerPoint slides: 1241 Elo (source: Design Arena, read October 21, 2026) - LiveBench reasoning: 91.2% (source: LiveBench, read October 21, 2026) - LiveBench data analysis: 75.3% (source: LiveBench, read October 21, 2026) - LiveBench research: 84.5% (source: LiveBench, read October 21, 2026) - LiveBench browser: 64.0% (source: LiveBench, read October 21, 2026) - LiveBench long agentic: 40.7% (source: LiveBench, read October 21, 2026) - LiveBench design: 79.8% (source: LiveBench, read October 21, 2026) - LiveCodeBench (Vals AI): 88.2% (source: Vals AI boards, read October 21, 2026) - SWE-bench Verified (Vals AI): 95.6% (source: Vals AI boards, read October 21, 2026) - Terminal-Bench 4 (Vals AI): 17.2% (source: Vals AI boards, read October 21, 2026) - Vibe Code Bench (Vals AI): 76.2% (source: Vals AI boards, read October 21, 2026) - Code migration (Vals AI): 44.6% (source: Vals AI boards, read October 21, 2026) - ProgramBench (Vals AI): 1.0% (source: Vals AI boards, read October 21, 2026) - IOI (Vals AI): 47.6% (source: Vals AI boards, read October 21, 2026) - Terminal-Bench 2.1 (Vals AI): 78.3% (source: Vals AI boards, read October 21, 2026) - Vibe Code Bench 1-100 (Vals AI): 14.8% (source: Vals AI boards, read October 21, 2026) - SkillsBench (Vals AI): 55.8% (source: Vals AI boards, read October 21, 2026) - CyberBench (Vals AI): 67.7% (source: Vals AI boards, read October 21, 2026) - Finance Agent (Vals AI): 53.7% (source: Vals AI boards, read October 21, 2026) - Tax Agent Bench (Vals AI): 33.1% (source: Vals AI boards, read October 21, 2026) - Legal Research Bench (Vals AI): 48.1% (source: Vals AI boards, read October 21, 2026) - Excel Modeling Benchmark (Vals AI): 62.7% (source: Vals AI boards, read October 21, 2026) - BioMysteryBench (Vals AI): 72.2% (source: Vals AI boards, read October 21, 2026) - Terminal-Bench-Science (Vals AI): 11.4% (source: Vals AI boards, read October 21, 2026) - Vals Science Index: 38.1% (source: Vals AI boards, read October 21, 2026) - Time Horizon Index (Vals AI): 5.8% (source: Vals AI boards, read October 21, 2026) - Public Benefits Bench (Vals AI): 66.8% (source: Vals AI boards, read October 21, 2026) - MysteryMechanism (Vals AI): 30.6% (source: Vals AI boards, read October 21, 2026) - SAGE (Vals AI): 28.9% (source: Vals AI boards, read October 21, 2026) - LegalBench (Vals AI): 86.3% (source: Vals AI boards, read October 21, 2026) - CorpFin (Vals AI): 66.2% (source: Vals AI boards, read October 21, 2026) - TaxEval (Vals AI): 71.1% (source: Vals AI boards, read October 21, 2026) - MortgageTax (Vals AI): 64.2% (source: Vals AI boards, read October 21, 2026) - MedCode (Vals AI): 44.7% (source: Vals AI boards, read October 21, 2026) - MedScribe (Vals AI): 86.5% (source: Vals AI boards, read October 21, 2026) - GPQA Diamond (Artificial Analysis run): 94.9% (source: Artificial Analysis, read October 21, 2026) - Humanity's Last Exam (Artificial Analysis run): 44.1% (source: Artificial Analysis, read October 21, 2026) - SciCode: 56.5% (source: Artificial Analysis, read October 21, 2026) - Long context reasoning (AA-LCR): 81.0% (source: Artificial Analysis, read October 21, 2026) - FrontierCode: 48.0% (source: Epoch AI benchmarking hub, read October 21, 2026) - FrontierSWE: 25.3% (source: Epoch AI benchmarking hub, read October 21, 2026) - WeirdML: 67.3% (source: Epoch AI benchmarking hub, read October 21, 2026) - APEX-Agents: 65.3% (source: Epoch AI benchmarking hub, read October 21, 2026) - GPQA Diamond (Epoch AI run): 94.0% (source: Epoch AI benchmarking hub, read October 21, 2026) - ARC-AGI: 87.5% (source: Epoch AI benchmarking hub, read October 21, 2026) - ARC-AGI-2: 67.1% (source: Epoch AI benchmarking hub, read October 21, 2026) - SimpleBench: 75.9% (source: Epoch AI benchmarking hub, read October 21, 2026) - Chess puzzles: 33.0% (source: Epoch AI benchmarking hub, read October 21, 2026) - Mystery game puzzles: 34.0% (source: Epoch AI benchmarking hub, read October 21, 2026) - EBR-bench: 30.5% (source: Epoch AI benchmarking hub, read October 21, 2026) - OTIS Mock AIME: 99.2% (source: Epoch AI benchmarking hub, read October 21, 2026) - FrontierMath, tiers 1 to 3: 66.0% (source: Epoch AI benchmarking hub, read October 21, 2026) - FrontierMath, tier 4: 31.7% (source: Epoch AI benchmarking hub, read October 21, 2026) - ProofBench: 51.0% (source: Epoch AI benchmarking hub, read October 21, 2026) - SimpleQA Verified: 49.3% (source: Epoch AI benchmarking hub, read October 21, 2026) - DTBench: 97.3% (source: Epoch AI benchmarking hub, read October 21, 2026) - LMCA: 48.5% (source: Epoch AI benchmarking hub, read October 21, 2026) - Furniture assembly: 40.0% (source: Epoch AI benchmarking hub, read October 21, 2026) - ALE-Bench: 1508.1 (source: ALE-Bench (Sakana AI), read October 21, 2026) - Vending-Bench 2: $9,047 (source: Epoch AI benchmarking hub, read October 21, 2026) - Epoch Capabilities Index: 156.6 (source: Epoch AI benchmarking hub, read October 21, 2026) - LMArena Text: 1429 Elo (source: LMArena (Hugging Face dataset), read October 21, 2026) - LMArena Text: coding: 1466 Elo (source: LMArena (Hugging Face dataset), read October 21, 2026) - LMArena Text: hard prompts: 1448 Elo (source: LMArena (Hugging Face dataset), read October 21, 2026) - LMArena Text: math: 1417 Elo (source: LMArena (Hugging Face dataset), read October 21, 2026) - LMArena Text: instruction following: 1431 Elo (source: LMArena (Hugging Face dataset), read October 21, 2026) - LMArena Text: creative writing: 1426 Elo (source: LMArena (Hugging Face dataset), read October 21, 2026) - LMArena Vision: 1263 Elo (source: LMArena (Hugging Face dataset), read October 21, 2026) - LMArena Text: English: 1433 Elo (source: LMArena (Hugging Face dataset), read October 21, 2026) - LMArena Text: non-English: 1420 Elo (source: LMArena (Hugging Face dataset), read October 21, 2026) - LMArena Text: Chinese: 1476 Elo (source: LMArena (Hugging Face dataset), read October 21, 2026) - LMArena Text: German: 1426 Elo (source: LMArena (Hugging Face dataset), read October 21, 2026) - LMArena Text: Japanese: 1378 Elo (source: LMArena (Hugging Face dataset), read October 21, 2026) - LMArena Text: Korean: 1391 Elo (source: LMArena (Hugging Face dataset), read October 21, 2026) - LMArena Text: French: 1455 Elo (source: LMArena (Hugging Face dataset), read October 21, 2026) - LMArena Text: Spanish: 1414 Elo (source: LMArena (Hugging Face dataset), read October 21, 2026) - LMArena Text: Russian: 1421 Elo (source: LMArena (Hugging Face dataset), read October 21, 2026) - LMArena Text: Polish: 1430 Elo (source: LMArena (Hugging Face dataset), read October 21, 2026) - LMArena Text: multi-turn: 1425 Elo (source: LMArena (Hugging Face dataset), read October 21, 2026) - LMArena Text: longer queries: 1456 Elo (source: LMArena (Hugging Face dataset), read October 21, 2026) - LMArena Text: expert: 1469 Elo (source: LMArena (Hugging Face dataset), read October 21, 2026) - LMArena Text: hard prompts in English: 1445 Elo (source: LMArena (Hugging Face dataset), read October 21, 2026) - LMArena Text: software and IT: 1457 Elo (source: LMArena (Hugging Face dataset), read October 21, 2026) - LMArena Text: mathematical work: 1464 Elo (source: LMArena (Hugging Face dataset), read October 21, 2026) - LMArena Text: science: 1437 Elo (source: LMArena (Hugging Face dataset), read October 21, 2026) - LMArena Text: medicine and healthcare: 1420 Elo (source: LMArena (Hugging Face dataset), read October 21, 2026) - LMArena Text: legal and government: 1429 Elo (source: LMArena (Hugging Face dataset), read October 21, 2026) - LMArena Text: business and finance: 1416 Elo (source: LMArena (Hugging Face dataset), read October 21, 2026) - LMArena Text: writing and language: 1429 Elo (source: LMArena (Hugging Face dataset), read October 21, 2026) - LMArena Text: entertainment and media: 1421 Elo (source: LMArena (Hugging Face dataset), read October 21, 2026) - LMArena WebDev: React: 1631 Elo (source: LMArena (Hugging Face dataset), read October 21, 2026) - LMArena WebDev: HTML: 1597 Elo (source: LMArena (Hugging Face dataset), read October 21, 2026) - LMArena WebDev: from an image: 1603 Elo (source: LMArena (Hugging Face dataset), read October 21, 2026) - LMArena Vision: English: 1270 Elo (source: LMArena (Hugging Face dataset), read October 21, 2026) - LMArena Vision: Chinese: 1289 Elo (source: LMArena (Hugging Face dataset), read October 21, 2026) - LMArena Vision: reading text: 1272 Elo (source: LMArena (Hugging Face dataset), read October 21, 2026) - LMArena Vision: diagrams: 1285 Elo (source: LMArena (Hugging Face dataset), read October 21, 2026) - LMArena Vision: homework: 1283 Elo (source: LMArena (Hugging Face dataset), read October 21, 2026) - LMArena Vision: humor: 1270 Elo (source: LMArena (Hugging Face dataset), read October 21, 2026) - LMArena Vision: creative writing: 1262 Elo (source: LMArena (Hugging Face dataset), read October 21, 2026) - LMArena Document: 1452 Elo (source: LMArena (Hugging Face dataset), read October 21, 2026)