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

Qwen3.8 27B (Non-reasoning)

  • Alibaba
  • Offene Gewichte
  • Ohne Reasoning

Intelligenz

Intelligence Index

#108 von 266
  1. 20,821GPT-5.6 Terra (Non-reasoning)
  2. 20,621K2 Horizon 7B
  3. 20,420Qwen3.5 Omni Plus
  4. 20,420DeepSeek V4 Pro 0813 (Non-reasoning)
  5. 20,220o3
  6. 20,220Qwen3.8 27B (Non-reasoning)
  7. 19,720K-EXAONE 2.0 0803
  8. 19,119LongCat 2.0
  9. 18,719JT-35B-Flash
  10. 18,519GPT-6 Luna (Non-reasoning)
Daten von Artificial Analysis

Bewertungen

  • AA-Omniscience Accuracy8,6%#230
  • Humanity's Last Exam12,1%#129
  • Terminal-Bench 4.00%#96
  • AA-LCR69,3%#111
  • SciCode36,2%#119
  • CritPt0,3%#117
  • MMMU-Pro69,9%#63
  • GPQA Diamond81,8%#66
  • τ²-Bench Banking20%#47
Qwen3.8 27B (Non-reasoning)Median
Daten von Artificial Analysis

Geschwindigkeit und Preis

Geschwindigkeit

Tokens pro Sekunde · #145 von 162
  1. 5252GPT-6.1 Sol (Low)
  2. 5252Llama 4 Maverick
  3. 5252Qwen3.8-Flash-Next
  4. 5151Granite 4.2 3B
  5. 5151GPT-6.1 Sol (Medium)
  6. 5050Qwen3.8 27B (Non-reasoning)
  7. 4949Qwen3.8 27B (Low)
  8. 4848Qwen3.8 27B (Medium)
  9. 4848Granite 4.2 30B
  10. 4646Phi-4 Mini Instruct
Daten von Artificial Analysis

Latenz

Sekunden bis zum ersten Token · #116 von 162
  1. 3,63,6Mercury 2.5
  2. 3,73,7Ring-2.6-1T
  3. 3,83,8MiMo-V2.6-Flash
  4. 3,93,9Qwen3.8 27B (Xhigh)
  5. 3,93,9Qwen3.8 27B (Low)
  6. 44Qwen3.8 27B (Non-reasoning)
  7. 44Qwen3.8 27B (Medium)
  8. 44GPT-6.1 Sol (Medium)
  9. 5,15,1GPT-6 Astra (Medium)
  10. 5,25,2Claude Fable 5.1 (Medium)
Daten von Artificial Analysis

Preis

$ pro 1M Tokens (3:1) · #103 von 169
  1. $1,11,1Qwen3.5 122B A10B (Reasoning)
  2. $1,131,13Qwen3.8 27B (Xhigh)
  3. $1,131,13Qwen3.8 27B (Medium)
  4. $1,131,13Qwen3.8 27B (Low)
  5. $1,131,13Nemotron 3 Ultra 550B A55B (Reasoning)
  6. $1,131,13Qwen3.8 27B (Non-reasoning)
  7. $1,31,3LongCat 2.0
  8. $1,351,35Qwen3.5 397B A17B (Non-reasoning)
  9. $1,351,35Qwen3.5 397B A17B (Reasoning)
  10. $1,431,43Step 5 Preview
Daten von Artificial Analysis

Ähnliche Modelle

  • GPT-5.6 Terra (Non-reasoning)OpenAI20,8
  • K2 Horizon 7BInstitute of Foundation Models20,6
  • Qwen3.5 Omni PlusAlibaba20,4
  • DeepSeek V4 Pro 0813 (Non-reasoning)DeepSeek20,4
  • o3OpenAI20,2
  • K-EXAONE 2.0 0803LG AI Research19,7
  • LongCat 2.0LongCat19,1
  • JT-35B-FlashChina Mobile18,7
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