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

Qwen3.5 4B (Non-reasoning)

  • Alibaba
  • Offene Gewichte
  • Ohne Reasoning

Intelligenz

Intelligence Index

#162 von 266
  1. 11,111Ling 3.0 Tiny
  2. 11,111Nova 2.0 Omni (Low)
  3. 1111Mi:dm K 2.5 Pro
  4. 10,811Trinity Large Thinking
  5. 10,811G9v3-3B
  6. 10,811Qwen3.5 4B (Non-reasoning)
  7. 10,611INTELLECT-3 (Based on GLM-4.5-Air)
  8. 10,410Solar Open 100B (Reasoning)
  9. 10,310Nemotron 3 Nano Omni 30B A3B Reasoning
  10. 10,210gpt-oss-120b (Low)
Daten von Artificial Analysis

Bewertungen

  • AA-Omniscience Accuracy11,2%#211
  • Humanity's Last Exam8%#169
  • AA-LCR34,7%#169
  • CritPt0%#143
  • MMMU-Pro62,1%#84
  • GPQA Diamond71,2%#114
  • IFBench33,3%#113
  • τ²-Bench Telecom87,7%#18
  • τ²-Bench Banking4,3%#94
  • Terminal-Bench Hard11,4%#53
Qwen3.5 4B (Non-reasoning)Median
Daten von Artificial Analysis

Geschwindigkeit und Preis

Geschwindigkeit

Tokens pro Sekunde · #162 von 162
  1. 4343Hermes 4 - Llama-3.1 405B (Non-reasoning)
  2. 4343Hermes 4 - Llama-3.1 405B (Reasoning)
  3. 4141Qwen3.8 2.4T A95B
  4. 4040Qwen3.8 Max (0902)
  5. 3939Phi-4
  6. 3535Gemma 4 31B (Reasoning)
  7. 3333Command A
  8. 2626Llama 3.2 Instruct 11B (Vision)
  9. 1919Qwen3.5 4B (Reasoning)
  10. 1414Qwen3.5 4B (Non-reasoning)
Daten von Artificial Analysis

Latenz

Sekunden bis zum ersten Token · #29 von 162
  1. 0,90,9Ministral 3 8B
  2. 0,90,9Mistral Small 4 (Reasoning)
  3. 0,90,9GPT-6 Luna (Non-reasoning)
  4. 0,90,9GPT-5.5 Instant (June 2026)
  5. 0,90,9Qwen3.5 9B (Non-reasoning)
  6. 0,90,9Qwen3.5 4B (Non-reasoning)
  7. 0,90,9Gemma 4 E4B (Reasoning)
  8. 0,90,9Gemma 4 26B A4B (Reasoning)
  9. 0,90,9Qwen3.5 4B (Reasoning)
  10. 0,90,9Qwen3 Coder Next
Daten von Artificial Analysis

Preis

$ pro 1M Tokens (3:1) · #11 von 169
  1. $00Tiny Aya Global
  2. $0,040,04Gemma 4 E4B (Reasoning)
  3. $0,040,04Gemma 4 E4B (Non-reasoning)
  4. $0,050,05Granite 4.2 3B
  5. $0,060,06Qwen3.5 4B (Reasoning)
  6. $0,060,06Qwen3.5 4B (Non-reasoning)
  7. $0,060,06Nova Micro
  8. $0,070,07NVIDIA Nemotron Nano 9B V2 (Reasoning)
  9. $0,070,07Sarvam 105B (High)
  10. $0,090,09NVIDIA Nemotron Nano 9B V2 (Non-reasoning)
Daten von Artificial Analysis

Ähnliche Modelle

  • Ling 3.0 TinyInclusionAI11,1
  • Nova 2.0 Omni (Low)Amazon11,1
  • Mi:dm K 2.5 ProKorea Telecom11
  • Trinity Large ThinkingArcee AI10,8
  • G9v3-3BAI9Stars10,8
  • INTELLECT-3 (Based on GLM-4.5-Air)Prime Intellect10,6
  • Solar Open 100B (Reasoning)Upstage10,4
  • Nemotron 3 Nano Omni 30B A3B ReasoningNVIDIA10,3
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