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

Qwen3.5 397B A17B (Non-reasoning)

  • Alibaba
  • Offene Gewichte
  • Ohne Reasoning

Intelligenz

Intelligence Index

#101 von 266
  1. 22,222Gemini 3.5 Flash-Lite
  2. 21,822G9v3-39A5B
  3. 21,722KAT Coder Pro V2
  4. 21,522GPT-6 Luna (Low)
  5. 21,522A.X-K2
  6. 21,421Qwen3.5 397B A17B (Non-reasoning)
  7. 21,421Nemotron 3.5 Bolt 74B-A9B
  8. 20,821GPT-5.6 Terra (Non-reasoning)
  9. 20,621K2 Horizon 7B
  10. 20,420Qwen3.5 Omni Plus
Daten von Artificial Analysis

Bewertungen

  • AA-Omniscience Accuracy24,5%#93
  • Humanity's Last Exam19,8%#103
  • AA-LCR64,3%#119
  • CritPt0,9%#106
  • MMMU-Pro52,7%#99
  • GPQA Diamond86,1%#43
  • IFBench51,6%#59
  • τ²-Bench Telecom83,9%#29
  • Terminal-Bench Hard35,6%#15
Qwen3.5 397B A17B (Non-reasoning)Median
Daten von Artificial Analysis

Geschwindigkeit und Preis

Geschwindigkeit

Tokens pro Sekunde · #122 von 162
  1. 6666North Mini Code
  2. 6464Kimi K2.7 Code
  3. 6363Claude Fable 5.1 (Xhigh)
  4. 6262GPT-6 Astra (Xhigh)
  5. 6161Qwen3.5 9B (Reasoning)
  6. 6060Qwen3.5 397B A17B (Non-reasoning)
  7. 5959Qwen3.5 397B A17B (Reasoning)
  8. 5959GPT-6.1 Sol (Max)
  9. 5858Claude Fable 5.1 (High)
  10. 5858Ling 3.0 Tiny
Daten von Artificial Analysis

Latenz

Sekunden bis zum ersten Token · #83 von 162
  1. 22Qwen3.5 Omni Plus
  2. 22Qwen3.6 35B A3B (Non-reasoning)
  3. 2,12,1GPT-6.1 Sol (Low)
  4. 2,12,1Qwen3.6 35B A3B (Reasoning)
  5. 2,12,1Qwen3.8-Flash-Next
  6. 2,22,2Qwen3.5 397B A17B (Non-reasoning)
  7. 2,22,2Qwen3.5 397B A17B (Reasoning)
  8. 2,22,2K2 Horizon 375B A23B
  9. 2,22,2GPT-5.6 Terra (High)
  10. 2,22,2Gemma 4 12B (Reasoning)
Daten von Artificial Analysis

Preis

$ pro 1M Tokens (3:1) · #105 von 169
  1. $1,131,13Qwen3.8 27B (Medium)
  2. $1,131,13Qwen3.8 27B (Low)
  3. $1,131,13Nemotron 3 Ultra 550B A55B (Reasoning)
  4. $1,131,13Qwen3.8 27B (Non-reasoning)
  5. $1,31,3LongCat 2.0
  6. $1,351,35Qwen3.5 397B A17B (Non-reasoning)
  7. $1,351,35Qwen3.5 397B A17B (Reasoning)
  8. $1,431,43Step 5 Preview
  9. $1,51,5Gemini 3.8 Flash (High)
  10. $1,51,5Gemini 3.8 Flash (Medium)
Daten von Artificial Analysis

Ähnliche Modelle

  • Gemini 3.5 Flash-LiteGoogle22,2
  • G9v3-39A5BAI9Stars21,8
  • KAT Coder Pro V2KwaiKAT21,7
  • GPT-6 Luna (Low)OpenAI21,5
  • A.X-K2SK Telecom21,5
  • Nemotron 3.5 Bolt 74B-A9BNVIDIA21,4
  • GPT-5.6 Terra (Non-reasoning)OpenAI20,8
  • K2 Horizon 7BInstitute of Foundation Models20,6
Daten von Artificial Analysis

Gleiches Labor

  • Qwen3.8 Max (0902)Alibaba45,4
  • Qwen3.8 2.4T A95BAlibaba39,9
  • Qwen3.8-Flash-NextAlibaba39,8
  • Qwen3.8 27B (Xhigh)Alibaba33,7
  • Qwen3.8 27B (Medium)Alibaba27,6
  • Qwen3.8 27B (Low)Alibaba26,2
  • Qwen3.7 PlusAlibaba25,2
  • Qwen3.5 Omni PlusAlibaba20,4
Daten von Artificial Analysis
HorizonVascend IDEOlympusTalosKurseCommunityBenchmark
DiscordGitHubXKontaktRechtlichesDatenschutzCookiesDatennutzungSicherheit
© 2026 Vascend Technologies · VAT IT04911550616
ascend