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

Qwen3.5 122B A10B (Non-reasoning)

  • Alibaba
  • Offene Gewichte
  • Ohne Reasoning

Intelligenz

Intelligence Index

#115 von 266
  1. 19,119LongCat 2.0
  2. 18,719JT-35B-Flash
  3. 18,519GPT-6 Luna (Non-reasoning)
  4. 18,418Qwen3.5 397B A17B (Reasoning)
  5. 18,218Qwen3.6 35B A3B (Reasoning)
  6. 17,718Qwen3.5 122B A10B (Non-reasoning)
  7. 17,518Muse Glimmer (High)
  8. 16,917Doubao Seed Code
  9. 16,717Gemma 4 26B A4B (Reasoning)
  10. 16,617Ring-2.6-1T
Daten von Artificial Analysis

Bewertungen

  • AA-Omniscience Accuracy19,1%#119
  • Humanity's Last Exam15,9%#114
  • AA-LCR61,3%#127
  • CritPt0,9%#106
  • MMMU-Pro70,3%#61
  • GPQA Diamond82,7%#61
  • IFBench50,8%#62
  • τ²-Bench Telecom84,5%#27
  • τ²-Bench Banking10,3%#69
  • Terminal-Bench Hard29,6%#21
Qwen3.5 122B A10B (Non-reasoning)Median
Daten von Artificial Analysis

Geschwindigkeit und Preis

Geschwindigkeit

Tokens pro Sekunde · #48 von 162
  1. 158158Nemotron 3 Ultra 550B A55B (Reasoning)
  2. 152152GPT-5.5 Instant (June 2026)
  3. 152152o3
  4. 151151Muse Spark Open (Xhigh)
  5. 147147Qwen3.6 35B A3B (Non-reasoning)
  6. 143143Qwen3.5 122B A10B (Non-reasoning)
  7. 140140GPT-6 Luna (Max)
  8. 137137Gemini 3.8 Flash (High)
  9. 136136Apertus 8B Instruct
  10. 134134Claude Sonnet 5.5 (Max)
Daten von Artificial Analysis

Latenz

Sekunden bis zum ersten Token · #92 von 162
  1. 2,22,2Gemma 4 12B (Reasoning)
  2. 2,32,3Gemma 4 12B (Non-reasoning)
  3. 2,32,3Qwen3.5 122B A10B (Reasoning)
  4. 2,32,3Hermes 4 - Llama-3.1 405B (Non-reasoning)
  5. 2,32,3Qwen3.7 Plus
  6. 2,32,3Qwen3.5 122B A10B (Non-reasoning)
  7. 2,32,3Hermes 4 - Llama-3.1 405B (Reasoning)
  8. 2,32,3GPT-6 Astra (Low)
  9. 2,42,4Mistral Medium 3.5
  10. 2,42,4GLM-5.3 (Max)
Daten von Artificial Analysis

Preis

$ pro 1M Tokens (3:1) · #97 von 169
  1. $0,850,85Nova 2.0 Lite (High)
  2. $0,850,85Nova 2.0 Lite (Medium)
  3. $0,850,85Nova 2.0 Lite (Low)
  4. $0,850,85Nova 2.0 Lite (Non-reasoning)
  5. $0,980,98Apodex 1.1
  6. $1,11,1Qwen3.5 122B A10B (Non-reasoning)
  7. $1,11,1Qwen3.5 122B A10B (Reasoning)
  8. $1,131,13Qwen3.8 27B (Xhigh)
  9. $1,131,13Qwen3.8 27B (Medium)
  10. $1,131,13Qwen3.8 27B (Low)
Daten von Artificial Analysis

Ähnliche Modelle

  • LongCat 2.0LongCat19,1
  • JT-35B-FlashChina Mobile18,7
  • GPT-6 Luna (Non-reasoning)OpenAI18,5
  • Qwen3.5 397B A17B (Reasoning)Alibaba18,4
  • Qwen3.6 35B A3B (Reasoning)Alibaba18,2
  • Muse Glimmer (High)Meta17,5
  • Doubao Seed CodeByteDance Seed16,9
  • Gemma 4 26B A4B (Reasoning)Google16,7
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 397B A17B (Non-reasoning)Alibaba21,4
Daten von Artificial Analysis
HorizonVascend IDEOlympusTalosKurseCommunityBenchmark
DiscordGitHubXKontaktRechtlichesDatenschutzCookiesDatennutzungSicherheit
© 2026 Vascend Technologies · VAT IT04911550616
ascend