Vascend
HorizonVascend IDEVascend CLICommunityBenchmarkKontakt
AnmeldenDiscord beitreten
StartHorizonIDECLIAnmelden
ChangelogIntelligenzKosten pro AufgabeCoding Agent IndexCyber IndexDecision IndexBenchmarksGeschwindigkeitLatenzPreisRangliste
Benchmark

GPT-6 Luna (Non-reasoning)

  • OpenAI
  • Proprietär
  • Ohne Reasoning

Intelligenz

Intelligence Index

#112 von 266
  1. 20,220o3
  2. 20,220Qwen3.8 27B (Non-reasoning)
  3. 19,720K-EXAONE 2.0 0803
  4. 19,119LongCat 2.0
  5. 18,719JT-35B-Flash
  6. 18,519GPT-6 Luna (Non-reasoning)
  7. 18,418Qwen3.5 397B A17B (Reasoning)
  8. 18,218Qwen3.6 35B A3B (Reasoning)
  9. 17,718Qwen3.5 122B A10B (Non-reasoning)
  10. 17,518Muse Glimmer (High)
Daten von Artificial Analysis

Bewertungen

  • AA-Omniscience Accuracy31,9%#73
  • Humanity's Last Exam8,6%#167
  • Terminal-Bench 4.01,5%#72
  • AA-LCR39,7%#158
  • SciCode43,1%#92
  • CritPt1,1%#103
  • MMMU-Pro62,1%#84
GPT-6 Luna (Non-reasoning)Median
Daten von Artificial Analysis

Geschwindigkeit und Preis

Geschwindigkeit

Tokens pro Sekunde · #64 von 162
  1. 127127Nova 2.0 Pro Preview (Medium)
  2. 124124Ring-2.6-1T
  3. 122122NVIDIA Nemotron Nano 9B V2 (Reasoning)
  4. 122122GPT-5.6 Terra (Non-reasoning)
  5. 122122Qwen3.5 Omni Plus
  6. 120120GPT-6 Luna (Non-reasoning)
  7. 120120Nova 2.0 Pro Preview (Low)
  8. 120120GPT-6 Luna (High)
  9. 119119Ministral 3 8B
  10. 119119GPT-5.6 Terra (High)
Daten von Artificial Analysis

Latenz

Sekunden bis zum ersten Token · #26 von 162
  1. 0,80,8Granite 4.2 30B
  2. 0,80,8Nemotron 3 Nano Omni 30B A3B Reasoning
  3. 0,90,9Phi-4 Mini Instruct
  4. 0,90,9Ministral 3 8B
  5. 0,90,9Mistral Small 4 (Reasoning)
  6. 0,90,9GPT-6 Luna (Non-reasoning)
  7. 0,90,9GPT-5.5 Instant (June 2026)
  8. 0,90,9Qwen3.5 9B (Non-reasoning)
  9. 0,90,9Qwen3.5 4B (Non-reasoning)
  10. 0,90,9Gemma 4 E4B (Reasoning)
Daten von Artificial Analysis

Preis

$ pro 1M Tokens (3:1) · #47 von 169
  1. $0,20,2Claude Haiku 5.5 (Medium)
  2. $0,20,2GPT-6 Luna (High)
  3. $0,20,2GPT-6 Luna (Medium)
  4. $0,20,2Claude Haiku 5.5 (Low)
  5. $0,20,2GPT-6 Luna (Low)
  6. $0,20,2GPT-6 Luna (Non-reasoning)
  7. $0,20,2Ministral 3 14B
  8. $0,220,22Phi-4
  9. $0,220,22Gemma 4 31B (Non-reasoning)
  10. $0,230,23Qwen3.8-Flash-Next
Daten von Artificial Analysis

Ähnliche Modelle

  • o3OpenAI20,2
  • Qwen3.8 27B (Non-reasoning)Alibaba20,2
  • K-EXAONE 2.0 0803LG AI Research19,7
  • LongCat 2.0LongCat19,1
  • JT-35B-FlashChina Mobile18,7
  • Qwen3.5 397B A17B (Reasoning)Alibaba18,4
  • Qwen3.6 35B A3B (Reasoning)Alibaba18,2
  • Qwen3.5 122B A10B (Non-reasoning)Alibaba17,7
Daten von Artificial Analysis

Gleiches Labor

  • 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
Daten von Artificial Analysis
HorizonVascend IDEOlympusTalosKurseCommunityBenchmark
DiscordGitHubXKontaktRechtlichesDatenschutzCookiesDatennutzungSicherheit
© 2026 Vascend Technologies · VAT IT04911550616
ascend