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

Qwen3.5 9B (Reasoning)

  • Alibaba
  • Veröffentlichung · 2. März 2026
  • Offene Gewichte
  • Reasoning

Intelligenz

Intelligence Index

#154 von 266
  1. 11,612gpt-oss-120b (High)
  2. 11,512K2 Think V2
  3. 11,512LongCat Flash Lite
  4. 11,411HyperCLOVA X SEED Think (32B)
  5. 11,311Mistral Small 4 (Reasoning)
  6. 11,211Qwen3.5 9B (Reasoning)
  7. 11,211Qwen3 Next 80B A3B (Reasoning)
  8. 11,111Granite 4.2 8B
  9. 11,111Ling 3.0 Tiny
  10. 11,111Nova 2.0 Omni (Low)
Daten von Artificial Analysis

Bewertungen

  • AA-Omniscience Accuracy16,4%#159
  • Humanity's Last Exam14,9%#117
  • Terminal-Bench 4.00,5%#86
  • AA-LCR70%#104
  • SciCode29,5%#126
  • CritPt0,3%#117
  • MMMU-Pro69,3%#65
  • GPQA Diamond80,6%#70
  • IFBench66,7%#23
  • τ²-Bench Telecom86,8%#21
  • τ²-Bench Banking7%#75
  • Terminal-Bench Hard24,2%#29
Qwen3.5 9B (Reasoning)Median
Daten von Artificial Analysis

Geschwindigkeit und Preis

Geschwindigkeit

Tokens pro Sekunde · #121 von 162
  1. 6666GPT-6 Astra (Max)
  2. 6666North Mini Code
  3. 6464Kimi K2.7 Code
  4. 6363Claude Fable 5.1 (Xhigh)
  5. 6262GPT-6 Astra (Xhigh)
  6. 6161Qwen3.5 9B (Reasoning)
  7. 6060Qwen3.5 397B A17B (Non-reasoning)
  8. 5959Qwen3.5 397B A17B (Reasoning)
  9. 5959GPT-6.1 Sol (Max)
  10. 5858Claude Fable 5.1 (High)
Daten von Artificial Analysis

Latenz

Sekunden bis zum ersten Token · #77 von 162
  1. 1,81,8Ling 3.1 Flash
  2. 1,81,8Gemma 4 31B (Non-reasoning)
  3. 1,81,8Qwen3 Omni 30B A3B Instruct
  4. 1,91,9Solar Mini 4
  5. 1,91,9Qwen3 Omni 30B A3B (Reasoning)
  6. 1,91,9Qwen3.5 9B (Reasoning)
  7. 22Qwen3.5 Omni Plus
  8. 22Qwen3.6 35B A3B (Non-reasoning)
  9. 2,12,1GPT-6.1 Sol (Low)
  10. 2,12,1Qwen3.6 35B A3B (Reasoning)
Daten von Artificial Analysis

Preis

$ pro 1M Tokens (3:1) · #30 von 169
  1. $0,140,14Phi-4 Multimodal Instruct
  2. $0,150,15Agnes 2.5 Pro Beta
  3. $0,150,15Gemma 4 12B (Reasoning)
  4. $0,150,15Gemma 4 12B (Non-reasoning)
  5. $0,150,15Ministral 3 8B
  6. $0,150,15Qwen3.5 9B (Reasoning)
  7. $0,160,16Gemma 4 26B A4B (Reasoning)
  8. $0,170,17Quasar 438B (Max, Based on GLM-5.2)
  9. $0,180,18MiMo-V2.6-Flash
  10. $0,180,18Solar Mini 4
Daten von Artificial Analysis

Ähnliche Modelle

  • gpt-oss-120b (High)OpenAI11,6
  • K2 Think V2Institute of Foundation Models11,5
  • LongCat Flash LiteLongCat11,5
  • HyperCLOVA X SEED Think (32B)Naver11,4
  • Mistral Small 4 (Reasoning)Mistral11,3
  • Qwen3 Next 80B A3B (Reasoning)Alibaba11,2
  • Granite 4.2 8BIBM11,1
  • Ling 3.0 TinyInclusionAI11,1
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