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

Qwen3.5 9B (Non-reasoning)

  • Alibaba
  • Offene Gewichte
  • Ohne Reasoning

Intelligenz

Intelligence Index

#132 von 266
  1. 14,214Gemma 4 12B (Reasoning)
  2. 13,914Gemma 4 31B (Non-reasoning)
  3. 13,614Nova 2.0 Omni (Medium)
  4. 13,413Nova 2.0 Lite (High)
  5. 13,413Apriel-v1.6-15B-Thinker
  6. 13,313Qwen3.5 9B (Non-reasoning)
  7. 13,213EXAONE 4.5 33B (Reasoning)
  8. 13,113Qwen3.5 4B (Reasoning)
  9. 13,113Gemma 4 26B A4B (Non-reasoning)
  10. 13,113Command A+
Daten von Artificial Analysis

Bewertungen

  • AA-Omniscience Accuracy14%#188
  • Humanity's Last Exam9,4%#160
  • AA-LCR46%#151
  • CritPt0,6%#112
  • MMMU-Pro66,8%#69
  • GPQA Diamond78,6%#74
  • IFBench37,8%#97
  • τ²-Bench Telecom85,1%#25
  • Terminal-Bench Hard18,2%#37
Qwen3.5 9B (Non-reasoning)Median
Daten von Artificial Analysis

Geschwindigkeit und Preis

Geschwindigkeit

Tokens pro Sekunde · #109 von 162
  1. 8282Claude Opus 5.5 (Xhigh)
  2. 8282Claude Opus 5.5 (Low)
  3. 8181Gemini 4 Argon (High)
  4. 8181Hy3
  5. 8080Claude Opus 5.5 (High)
  6. 8080Qwen3.5 9B (Non-reasoning)
  7. 7878Grok 4.7 (Low)
  8. 7777Ministral 3 14B
  9. 7777Magistral Small 1.2
  10. 7676LongCat 2.0
Daten von Artificial Analysis

Latenz

Sekunden bis zum ersten Token · #28 von 162
  1. 0,90,9Phi-4 Mini Instruct
  2. 0,90,9Ministral 3 8B
  3. 0,90,9Mistral Small 4 (Reasoning)
  4. 0,90,9GPT-6 Luna (Non-reasoning)
  5. 0,90,9GPT-5.5 Instant (June 2026)
  6. 0,90,9Qwen3.5 9B (Non-reasoning)
  7. 0,90,9Qwen3.5 4B (Non-reasoning)
  8. 0,90,9Gemma 4 E4B (Reasoning)
  9. 0,90,9Gemma 4 26B A4B (Reasoning)
  10. 0,90,9Qwen3.5 4B (Reasoning)
Daten von Artificial Analysis

Preis

$ pro 1M Tokens (3:1) · #36 von 169
  1. $0,160,16Gemma 4 26B A4B (Reasoning)
  2. $0,170,17Quasar 438B (Max, Based on GLM-5.2)
  3. $0,180,18MiMo-V2.6-Flash
  4. $0,180,18Solar Mini 4
  5. $0,190,19Gemma 4 26B A4B (Non-reasoning)
  6. $0,190,19Qwen3.5 9B (Non-reasoning)
  7. $0,20,2Claude Haiku 5.5 (Max)
  8. $0,20,2Claude Haiku 5.5 (Xhigh)
  9. $0,20,2GPT-6 Luna (Max)
  10. $0,20,2Claude Haiku 5.5 (High)
Daten von Artificial Analysis

Ähnliche Modelle

  • Gemma 4 12B (Reasoning)Google14,2
  • Gemma 4 31B (Non-reasoning)Google13,9
  • Nova 2.0 Omni (Medium)Amazon13,6
  • Nova 2.0 Lite (High)Amazon13,4
  • Apriel-v1.6-15B-ThinkerServiceNow13,4
  • EXAONE 4.5 33B (Reasoning)LG AI Research13,2
  • Qwen3.5 4B (Reasoning)Alibaba13,1
  • Gemma 4 26B A4B (Non-reasoning)Google13,1
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