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

Qwen3.5 122B A10B (Reasoning)

  • Alibaba
  • Veröffentlichung · 24. Februar 2026
  • Offene Gewichte
  • Reasoning

Intelligenz

Intelligence Index

#121 von 266
  1. 17,518Muse Glimmer (High)
  2. 16,917Doubao Seed Code
  3. 16,717Gemma 4 26B A4B (Reasoning)
  4. 16,617Ring-2.6-1T
  5. 15,616K2 Horizon 3.7B
  6. 15,616Qwen3.5 122B A10B (Reasoning)
  7. 15,215Qwen3.6 35B A3B (Non-reasoning)
  8. 14,715Gemma 4 31B (Reasoning)
  9. 14,314ERNIE 5.0 Thinking Preview
  10. 14,214Nova 2.0 Pro Preview (Medium)
Daten von Artificial Analysis

Bewertungen

  • AA-Omniscience Accuracy24,4%#95
  • Humanity's Last Exam25,2%#91
  • Terminal-Bench 4.00%#96
  • AA-LCR76,3%#80
  • SciCode39,7%#107
  • CritPt0,6%#112
  • MMMU-Pro75%#48
  • GPQA Diamond85,7%#44
  • IFBench75,7%#9
  • τ²-Bench Telecom93,6%#6
  • τ²-Bench Banking15,3%#57
  • Terminal-Bench Hard31,1%#18
Qwen3.5 122B A10B (Reasoning)Median
Daten von Artificial Analysis

Geschwindigkeit und Preis

Geschwindigkeit

Tokens pro Sekunde · #57 von 162
  1. 134134Claude Sonnet 5.5 (Max)
  2. 133133Qwen3 Next 80B A3B Instruct
  3. 132132Gemini 3.1 Pro Preview
  4. 131131Qwen3.6 35B A3B (Reasoning)
  5. 130130GPT-5.6 Terra (Max)
  6. 128128Qwen3.5 122B A10B (Reasoning)
  7. 127127GPT-6 Luna (Xhigh)
  8. 127127Nova 2.0 Pro Preview (Medium)
  9. 124124Ring-2.6-1T
  10. 122122NVIDIA Nemotron Nano 9B V2 (Reasoning)
Daten von Artificial Analysis

Latenz

Sekunden bis zum ersten Token · #89 von 162
  1. 2,22,2Qwen3.5 397B A17B (Reasoning)
  2. 2,22,2K2 Horizon 375B A23B
  3. 2,22,2GPT-5.6 Terra (High)
  4. 2,22,2Gemma 4 12B (Reasoning)
  5. 2,32,3Gemma 4 12B (Non-reasoning)
  6. 2,32,3Qwen3.5 122B A10B (Reasoning)
  7. 2,32,3Hermes 4 - Llama-3.1 405B (Non-reasoning)
  8. 2,32,3Qwen3.7 Plus
  9. 2,32,3Qwen3.5 122B A10B (Non-reasoning)
  10. 2,32,3Hermes 4 - Llama-3.1 405B (Reasoning)
Daten von Artificial Analysis

Preis

$ pro 1M Tokens (3:1) · #98 von 169
  1. $0,850,85Nova 2.0 Lite (Medium)
  2. $0,850,85Nova 2.0 Lite (Low)
  3. $0,850,85Nova 2.0 Lite (Non-reasoning)
  4. $0,980,98Apodex 1.1
  5. $1,11,1Qwen3.5 122B A10B (Non-reasoning)
  6. $1,11,1Qwen3.5 122B A10B (Reasoning)
  7. $1,131,13Qwen3.8 27B (Xhigh)
  8. $1,131,13Qwen3.8 27B (Medium)
  9. $1,131,13Qwen3.8 27B (Low)
  10. $1,131,13Nemotron 3 Ultra 550B A55B (Reasoning)
Daten von Artificial Analysis

Ähnliche Modelle

  • Muse Glimmer (High)Meta17,5
  • Doubao Seed CodeByteDance Seed16,9
  • Gemma 4 26B A4B (Reasoning)Google16,7
  • Ring-2.6-1TInclusionAI16,6
  • K2 Horizon 3.7BInstitute of Foundation Models15,6
  • Qwen3.6 35B A3B (Non-reasoning)Alibaba15,2
  • Gemma 4 31B (Reasoning)Google14,7
  • ERNIE 5.0 Thinking PreviewBaidu14,3
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