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

Qwen3.6 35B A3B (Non-reasoning)

  • Alibaba
  • Offene Gewichte
  • Ohne Reasoning

Intelligenz

Intelligence Index

#122 von 266
  1. 16,917Doubao Seed Code
  2. 16,717Gemma 4 26B A4B (Reasoning)
  3. 16,617Ring-2.6-1T
  4. 15,616K2 Horizon 3.7B
  5. 15,616Qwen3.5 122B A10B (Reasoning)
  6. 15,215Qwen3.6 35B A3B (Non-reasoning)
  7. 14,715Gemma 4 31B (Reasoning)
  8. 14,314ERNIE 5.0 Thinking Preview
  9. 14,214Nova 2.0 Pro Preview (Medium)
  10. 14,214Mistral Medium 3.5
Daten von Artificial Analysis

Bewertungen

  • AA-Omniscience Accuracy16,7%#153
  • Humanity's Last Exam13,9%#122
  • AA-LCR64,3%#119
  • CritPt0%#143
  • MMMU-Pro71%#58
  • GPQA Diamond81,7%#67
  • IFBench36,2%#102
  • τ²-Bench Telecom85,1%#25
  • τ²-Bench Banking5,4%#87
  • Terminal-Bench Hard25,8%#25
Qwen3.6 35B A3B (Non-reasoning)Median
Daten von Artificial Analysis

Geschwindigkeit und Preis

Geschwindigkeit

Tokens pro Sekunde · #47 von 162
  1. 159159Quasar 438B (Max, Based on GLM-5.2)
  2. 158158Nemotron 3 Ultra 550B A55B (Reasoning)
  3. 152152GPT-5.5 Instant (June 2026)
  4. 152152o3
  5. 151151Muse Spark Open (Xhigh)
  6. 147147Qwen3.6 35B A3B (Non-reasoning)
  7. 143143Qwen3.5 122B A10B (Non-reasoning)
  8. 140140GPT-6 Luna (Max)
  9. 137137Gemini 3.8 Flash (High)
  10. 136136Apertus 8B Instruct
Daten von Artificial Analysis

Latenz

Sekunden bis zum ersten Token · #79 von 162
  1. 1,81,8Qwen3 Omni 30B A3B Instruct
  2. 1,91,9Solar Mini 4
  3. 1,91,9Qwen3 Omni 30B A3B (Reasoning)
  4. 1,91,9Qwen3.5 9B (Reasoning)
  5. 22Qwen3.5 Omni Plus
  6. 22Qwen3.6 35B A3B (Non-reasoning)
  7. 2,12,1GPT-6.1 Sol (Low)
  8. 2,12,1Qwen3.6 35B A3B (Reasoning)
  9. 2,12,1Qwen3.8-Flash-Next
  10. 2,22,2Qwen3.5 397B A17B (Non-reasoning)
Daten von Artificial Analysis

Preis

$ pro 1M Tokens (3:1) · #89 von 169
  1. $0,660,66DeepSeek V4 Flash Vision (Max)
  2. $0,670,67Llama 3.3 Instruct 70B
  3. $0,70,7Qwen3.7 Plus
  4. $0,750,75Magistral Small 1.2
  5. $0,840,84Qwen3.6 35B A3B (Reasoning)
  6. $0,840,84Qwen3.6 35B A3B (Non-reasoning)
  7. $0,850,85Gemini 3.5 Flash-Lite
  8. $0,850,85Ring-2.6-1T
  9. $0,850,85Nova 2.0 Lite (High)
  10. $0,850,85Nova 2.0 Lite (Medium)
Daten von Artificial Analysis

Ähnliche Modelle

  • 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
  • Qwen3.5 122B A10B (Reasoning)Alibaba15,6
  • Gemma 4 31B (Reasoning)Google14,7
  • ERNIE 5.0 Thinking PreviewBaidu14,3
  • Nova 2.0 Pro Preview (Medium)Amazon14,2
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