Vascend
HorizonVascend IDEVascend CLICommunityBenchmarkContact
Sign inJoin Discord
HomeHorizonIDECLISign in
ChangelogIntelligenceCost per taskCoding Agent IndexCyber IndexDecision IndexBenchmarksSpeedLatencyPriceLeaderboard
Benchmark

GPT-6 Luna (Max)

  • OpenAI
  • Release · September 22, 2026
  • Proprietary
  • Reasoning

Intelligence

Intelligence Index

#50 of 266
  1. 39.940Qwen3.8 2.4T A95B
  2. 39.840Gemini 3.8 Flash (Medium)
  3. 39.840Qwen3.8-Flash-Next
  4. 38.939Muse Spark Open (Xhigh)
  5. 38.438Mistral Large 4 Preview
  6. 38.138GPT-6 Luna (Max)
  7. 3838GPT-5.6 Terra (Xhigh)
  8. 37.938MiMo-V2.6-Flash
  9. 37.838Claude Haiku 5.5 (High)
  10. 3636DeepSeek V4 Pro 0813 (Max)
Data from Artificial Analysis

Evaluations

  • AA-Briefcase1,336#21
  • AA-Omniscience Accuracy43.8%#45
  • AA-Omniscience Non-Hallucination23.3%#26
  • AutomationBench-AA53.2%#19
  • GDPval-AA1,433#20
  • Humanity's Last Exam38.5%#54
  • GDP.pdf22.8%#9
  • Terminal-Bench 4.012.6%#54
  • AA-LCR83.3%#13
  • SciCode54.6%#37
  • CritPt19.4%#37
  • Terminal-Bench-Science8.6%#15
  • FrontierCode41.9%#13
  • AA-AnalystAgent43.8%#12
  • Harvey LAB-AA3.3%#9
  • AA-3D1,000#8
  • MLCR-AA26.1%#7
  • MMMU-Pro79.7%#27
  • PersonalityBench: Expressiveness33.2#20
  • PersonalityBench: Organization18.3#26
  • PersonalityBench: Transparency57.9#13
  • PersonalityBench: Slop3.5#26
  • PersonalityBench: Informativeness13.4#26
  • PersonalityBench: Warmth40.6#18
  • PersonalityBench: Conviction45.6#17
  • PersonalityBench: Imagination15.8#25
GPT-6 Luna (Max)Median
Data from Artificial Analysis

Cost per task

Cost per task

$ per Intelligence Index task · #1 of 24
  1. $0.070.07GPT-6 Luna (Max)
  2. $0.130.13MiMo-V2.6-Pro
  3. $0.190.19Nemotron 3.5 Super VL
  4. $0.210.21Claude Haiku 5.5 (Max)
  5. $0.220.22MiniMax-M3.1-Flash
  6. $0.230.23Beam 1.0
  7. $0.260.26DeepSeek V4.1 Flash 1017 (Max)
  8. $0.280.28GLM-5.3-Flash
  9. $0.720.72GPT-6.1 Sol (Max)
  10. $0.840.84Muse Spark Open (Xhigh)
Data from Artificial Analysis

Time per task

seconds per task · #8 of 26
  1. 9696Nemotron 3.5 Super VL
  2. 165165Inkling (Xhigh)
  3. 263263Step 5 Preview
  4. 284284Muse Spark Open (Xhigh)
  5. 341341Muse Wonder (Max)
  6. 364364GPT-6 Luna (Max)
  7. 396396DeepSeek V4.1 Flash 1017 (Max)
  8. 412412GPT-6 Astra (Max)
  9. 428428Claude Haiku 5.5 (Max)
  10. 498498Gemini 3.8 Flash (High)
Data from Artificial Analysis

Tokens per task

output tokens per task · #7 of 27
  1. 27.2K27KGPT-6 Astra (Max)
  2. 34.7K35KInkling (Xhigh)
  3. 38.1K38KGPT-6.1 Sol (Max)
  4. 40.4K40KMuse Spark Open (Xhigh)
  5. 49.2K49KNemotron 3.5 Super VL
  6. 50K50KGPT-6 Luna (Max)
  7. 51.5K52KK2 Horizon 375B A23B
  8. 53.8K54KMuse Wonder Full (Max)
  9. 54.5K55KMuse Wonder (Max)
  10. 55.2K55KKimi K3.1 Pro
Data from Artificial Analysis

Speed and price

Speed

tokens per second · #49 of 162
  1. 152152GPT-5.5 Instant (June 2026)
  2. 152152o3
  3. 151151Muse Spark Open (Xhigh)
  4. 147147Qwen3.6 35B A3B (Non-reasoning)
  5. 143143Qwen3.5 122B A10B (Non-reasoning)
  6. 140140GPT-6 Luna (Max)
  7. 137137Gemini 3.8 Flash (High)
  8. 136136Apertus 8B Instruct
  9. 134134Claude Sonnet 5.5 (Max)
  10. 133133Qwen3 Next 80B A3B Instruct
Data from Artificial Analysis

Latency

seconds to first token · #152 of 162
  1. 40.741GPT-6 Astra (High)
  2. 54.955GPT-5.3 Codex (Xhigh)
  3. 5757Gemini 4 Argon (High)
  4. 59.560Claude Haiku 5.5 (Xhigh)
  5. 74.575Claude Fable 5.1 (Xhigh)
  6. 78.579GPT-6 Luna (Max)
  7. 102.7103GPT-5.6 Terra (Max)
  8. 106.6107GPT-6.1 Sol (Xhigh)
  9. 109.6110Claude Opus 5.5 (Xhigh)
  10. 161.5162GPT-6 Astra (Xhigh)
Data from Artificial Analysis

Price

$ per 1M tokens (3:1) · #39 of 169
  1. $0.180.18Solar Mini 4
  2. $0.190.19Gemma 4 26B A4B (Non-reasoning)
  3. $0.190.19Qwen3.5 9B (Non-reasoning)
  4. $0.20.2Claude Haiku 5.5 (Max)
  5. $0.20.2Claude Haiku 5.5 (Xhigh)
  6. $0.20.2GPT-6 Luna (Max)
  7. $0.20.2Claude Haiku 5.5 (High)
  8. $0.20.2GPT-6 Luna (Xhigh)
  9. $0.20.2Claude Haiku 5.5 (Medium)
  10. $0.20.2GPT-6 Luna (High)
Data from Artificial Analysis

Nearby models

  • Qwen3.8 2.4T A95BAlibaba39.9
  • Gemini 3.8 Flash (Medium)Google39.8
  • Qwen3.8-Flash-NextAlibaba39.8
  • Muse Spark Open (Xhigh)Meta38.9
  • Mistral Large 4 PreviewMistral38.4
  • GPT-5.6 Terra (Xhigh)OpenAI38
  • MiMo-V2.6-FlashXiaomi37.9
  • Claude Haiku 5.5 (High)Anthropic37.8
Data from Artificial Analysis

Same lab

  • GPT-6 Astra (Max)OpenAI52.7
  • GPT-6 Astra (Xhigh)OpenAI52.4
  • GPT-6.1 Sol (Max)OpenAI51.8
  • GPT-6.1 Sol (Xhigh)OpenAI51
  • GPT-6 Astra (High)OpenAI50.9
  • GPT-6.1 Sol (High)OpenAI50.2
  • GPT-6 Astra (Medium)OpenAI49.6
  • GPT-6.1 Sol (Medium)OpenAI47.8
Data from Artificial Analysis
HorizonVascend IDEOlympusTalosCoursesCommunityBenchmark
DiscordGitHubXLet’s talkLegalPrivacyCookiesData useSecurity
© 2026 Vascend Technologies · VAT IT04911550616
ascend