# OpenAI GPT-6 Luna As of October 22, 2026, OpenAI GPT-6 Luna ranks #45 of 123 models overall with 59.7 ±7.7 on the LLMBenchmark Index. GPT-6 Luna ranks #19 of 108 in math, its strongest category. OpenAI GPT-6 Luna costs $0.10 per million input tokens and $0.50 per million output tokens. GPT-6 Luna was released on September 22, 2026. Page: https://llmbenchmark.ai/models/gpt-6-luna Data from October 22, 2026. Every figure below names the board it was read from and the day. - Maker: OpenAI - Released: September 22, 2026 - Price per million input tokens: $0.10 - Price per million output tokens: $0.50 - Context window: 1.05M tokens - Overall rank: 45 of 123, by the LLMBenchmark Index - LLMBenchmark Index: 59.7 ±7.7 (90% margin, from 7 of 7 inputs) - Artificial Analysis Intelligence Index: 38.1 - Vibe Coding Index: 57.3 (from 5 of 6 coding benchmarks) Benchmark results (103 of 195): - LiveBench coding: 84.5% (source: LiveBench, read October 22, 2026) - LMArena WebDev: 1578 Elo (source: LMArena WebDev, read October 22, 2026) - Vals Index: 52.3% (source: Vals Index, read October 22, 2026) - AA Intelligence Index: 38.1 (source: Artificial Analysis (via OpenRouter), read October 22, 2026) - Design Arena: websites: 1271 Elo (source: Design Arena, read October 22, 2026) - Design Arena: UI components: 1295 Elo (source: Design Arena, read October 22, 2026) - Design Arena: game dev: 1257 Elo (source: Design Arena, read October 22, 2026) - Design Arena: data viz: 1216 Elo (source: Design Arena, read October 22, 2026) - Design Arena: 3D: 1218 Elo (source: Design Arena, read October 22, 2026) - Design Arena: all code categories: 1270 Elo (source: Design Arena, read October 22, 2026) - Design Arena: SVG: 1252 Elo (source: Design Arena, read October 22, 2026) - Design Arena: ASCII art: 1153 Elo (source: Design Arena, read October 22, 2026) - Design Arena: agents building web apps: 1191 Elo (source: Design Arena, read October 22, 2026) - Design Arena: agents building full-stack apps: 1158 Elo (source: Design Arena, read October 22, 2026) - Design Arena: agents building mobile apps: 1134 Elo (source: Design Arena, read October 22, 2026) - LiveBench reasoning: 81.8% (source: LiveBench, read October 22, 2026) - LiveBench data analysis: 73.4% (source: LiveBench, read October 22, 2026) - LiveBench research: 43.5% (source: LiveBench, read October 22, 2026) - LiveBench browser: 72.0% (source: LiveBench, read October 22, 2026) - LiveBench long agentic: 48.1% (source: LiveBench, read October 22, 2026) - LiveBench design: 82.5% (source: LiveBench, read October 22, 2026) - Terminal-Bench 4 (Vals AI): 13.6% (source: Vals AI boards, read October 22, 2026) - Vibe Code Bench (Vals AI): 81.7% (source: Vals AI boards, read October 22, 2026) - Code migration (Vals AI): 42.5% (source: Vals AI boards, read October 22, 2026) - ProgramBench (Vals AI): 0.5% (source: Vals AI boards, read October 22, 2026) - SREBench (Vals AI): 2.7% (source: Vals AI boards, read October 22, 2026) - IOI (Vals AI): 55.6% (source: Vals AI boards, read October 22, 2026) - Terminal-Bench 2.1 (Vals AI): 73.0% (source: Vals AI boards, read October 22, 2026) - SWE-bench Multimodal (Vals AI): 37.5% (source: Vals AI boards, read October 22, 2026) - CyberBench (Vals AI): 76.3% (source: Vals AI boards, read October 22, 2026) - Finance Agent (Vals AI): 49.9% (source: Vals AI boards, read October 22, 2026) - Tax Agent Bench (Vals AI): 19.9% (source: Vals AI boards, read October 22, 2026) - Legal Research Bench (Vals AI): 30.3% (source: Vals AI boards, read October 22, 2026) - Harvey's Legal Agent Benchmark (Vals AI): 4.2% (source: Vals AI boards, read October 22, 2026) - Excel Modeling Benchmark (Vals AI): 68.5% (source: Vals AI boards, read October 22, 2026) - BioMysteryBench (Vals AI): 61.5% (source: Vals AI boards, read October 22, 2026) - Terminal-Bench-Science (Vals AI): 4.3% (source: Vals AI boards, read October 22, 2026) - Vals Science Index: 28.4% (source: Vals AI boards, read October 22, 2026) - Public Benefits Bench (Vals AI): 57.6% (source: Vals AI boards, read October 22, 2026) - MysteryMechanism (Vals AI): 19.4% (source: Vals AI boards, read October 22, 2026) - SAGE (Vals AI): 48.1% (source: Vals AI boards, read October 22, 2026) - MedCode (Vals AI): 44.7% (source: Vals AI boards, read October 22, 2026) - MedScribe (Vals AI): 83.7% (source: Vals AI boards, read October 22, 2026) - Humanity's Last Exam (Artificial Analysis run): 38.5% (source: Artificial Analysis, read October 22, 2026) - SciCode: 54.6% (source: Artificial Analysis, read October 22, 2026) - Long context reasoning (AA-LCR): 83.3% (source: Artificial Analysis, read October 22, 2026) - FrontierCode: 42.4% (source: Epoch AI benchmarking hub, read October 22, 2026) - APEX-Agents: 44.3% (source: Epoch AI benchmarking hub, read October 22, 2026) - GPQA Diamond (Epoch AI run): 90.5% (source: Epoch AI benchmarking hub, read October 22, 2026) - ARC-AGI: 86.7% (source: Epoch AI benchmarking hub, read October 22, 2026) - ARC-AGI-2: 59.3% (source: Epoch AI benchmarking hub, read October 22, 2026) - Chess puzzles: 36.0% (source: Epoch AI benchmarking hub, read October 22, 2026) - Mystery game puzzles: 7.0% (source: Epoch AI benchmarking hub, read October 22, 2026) - OTIS Mock AIME: 98.9% (source: Epoch AI benchmarking hub, read October 22, 2026) - FrontierMath, tiers 1 to 3: 78.9% (source: Epoch AI benchmarking hub, read October 22, 2026) - FrontierMath, tier 4: 56.1% (source: Epoch AI benchmarking hub, read October 22, 2026) - ProofBench: 64.0% (source: Epoch AI benchmarking hub, read October 22, 2026) - SimpleQA Verified: 41.4% (source: Epoch AI benchmarking hub, read October 22, 2026) - DTBench: 90.1% (source: Epoch AI benchmarking hub, read October 22, 2026) - LMCA: 44.5% (source: Epoch AI benchmarking hub, read October 22, 2026) - Furniture assembly: 44.2% (source: Epoch AI benchmarking hub, read October 22, 2026) - SpireClimb: 0.0% (source: Epoch AI benchmarking hub, read October 22, 2026) - ALE-Bench: 1576.9 (source: ALE-Bench (Sakana AI), read October 22, 2026) - Epoch Capabilities Index: 156.8 (source: Epoch AI benchmarking hub, read October 22, 2026) - LMArena Text: 1389 Elo (source: LMArena (Hugging Face dataset), read October 22, 2026) - LMArena Text: coding: 1437 Elo (source: LMArena (Hugging Face dataset), read October 22, 2026) - LMArena Text: hard prompts: 1410 Elo (source: LMArena (Hugging Face dataset), read October 22, 2026) - LMArena Text: math: 1409 Elo (source: LMArena (Hugging Face dataset), read October 22, 2026) - LMArena Text: instruction following: 1408 Elo (source: LMArena (Hugging Face dataset), read October 22, 2026) - LMArena Text: creative writing: 1363 Elo (source: LMArena (Hugging Face dataset), read October 22, 2026) - LMArena Vision: 1216 Elo (source: LMArena (Hugging Face dataset), read October 22, 2026) - LMArena Text: English: 1393 Elo (source: LMArena (Hugging Face dataset), read October 22, 2026) - LMArena Text: non-English: 1381 Elo (source: LMArena (Hugging Face dataset), read October 22, 2026) - LMArena Text: Chinese: 1427 Elo (source: LMArena (Hugging Face dataset), read October 22, 2026) - LMArena Text: German: 1376 Elo (source: LMArena (Hugging Face dataset), read October 22, 2026) - LMArena Text: Japanese: 1369 Elo (source: LMArena (Hugging Face dataset), read October 22, 2026) - LMArena Text: Korean: 1359 Elo (source: LMArena (Hugging Face dataset), read October 22, 2026) - LMArena Text: French: 1408 Elo (source: LMArena (Hugging Face dataset), read October 22, 2026) - LMArena Text: Spanish: 1391 Elo (source: LMArena (Hugging Face dataset), read October 22, 2026) - LMArena Text: Russian: 1392 Elo (source: LMArena (Hugging Face dataset), read October 22, 2026) - LMArena Text: Polish: 1383 Elo (source: LMArena (Hugging Face dataset), read October 22, 2026) - LMArena Text: multi-turn: 1392 Elo (source: LMArena (Hugging Face dataset), read October 22, 2026) - LMArena Text: longer queries: 1408 Elo (source: LMArena (Hugging Face dataset), read October 22, 2026) - LMArena Text: expert: 1442 Elo (source: LMArena (Hugging Face dataset), read October 22, 2026) - LMArena Text: hard prompts in English: 1410 Elo (source: LMArena (Hugging Face dataset), read October 22, 2026) - LMArena Text: software and IT: 1423 Elo (source: LMArena (Hugging Face dataset), read October 22, 2026) - LMArena Text: mathematical work: 1427 Elo (source: LMArena (Hugging Face dataset), read October 22, 2026) - LMArena Text: science: 1386 Elo (source: LMArena (Hugging Face dataset), read October 22, 2026) - LMArena Text: medicine and healthcare: 1352 Elo (source: LMArena (Hugging Face dataset), read October 22, 2026) - LMArena Text: legal and government: 1400 Elo (source: LMArena (Hugging Face dataset), read October 22, 2026) - LMArena Text: business and finance: 1388 Elo (source: LMArena (Hugging Face dataset), read October 22, 2026) - LMArena Text: writing and language: 1384 Elo (source: LMArena (Hugging Face dataset), read October 22, 2026) - LMArena Text: entertainment and media: 1364 Elo (source: LMArena (Hugging Face dataset), read October 22, 2026) - LMArena WebDev: React: 1573 Elo (source: LMArena (Hugging Face dataset), read October 22, 2026) - LMArena WebDev: HTML: 1595 Elo (source: LMArena (Hugging Face dataset), read October 22, 2026) - LMArena WebDev: from an image: 1571 Elo (source: LMArena (Hugging Face dataset), read October 22, 2026) - LMArena Vision: English: 1204 Elo (source: LMArena (Hugging Face dataset), read October 22, 2026) - LMArena Vision: Chinese: 1266 Elo (source: LMArena (Hugging Face dataset), read October 22, 2026) - LMArena Vision: reading text: 1225 Elo (source: LMArena (Hugging Face dataset), read October 22, 2026) - LMArena Vision: diagrams: 1245 Elo (source: LMArena (Hugging Face dataset), read October 22, 2026) - LMArena Vision: homework: 1261 Elo (source: LMArena (Hugging Face dataset), read October 22, 2026) - LMArena Vision: creative writing: 1205 Elo (source: LMArena (Hugging Face dataset), read October 22, 2026) - FACTS Benchmark Suite: 63.3% (source: Kaggle Benchmarks, read October 22, 2026)