Vascend
HorizonVascend IDEVascend CLICommunityBenchmarkContatti
AccediEntra su Discord
HomeHorizonIDECLIAccedi
ChangelogIntelligenzaCosto per taskCoding Agent IndexCyber IndexDecision IndexBenchmarkVelocitàLatenzaPrezzoClassifica
Benchmark

Qwen3.8 27B (Medium)

  • Alibaba
  • Pesi aperti
  • Ragionamento

Intelligenza

Intelligence Index

#76 su 266
  1. 29,930GPT-6 Luna (Medium)
  2. 29,730Gemini 3.1 Pro Preview
  3. 29,530Claude Haiku 5.5 (Low)
  4. 29,229MiniMax-M3
  5. 28,228Nex-N2-Pro (Based on Qwen3.5-397B-A17B)
  6. 27,628Qwen3.8 27B (Medium)
  7. 27,528GPT-5.6 Terra (Low)
  8. 27,327JT-4.1 Flash 236B A21B (Non-reasoning)
  9. 26,727Quasar 438B (Max, Based on GLM-5.2)
  10. 26,627Solar Pro 4
Dati di Artificial Analysis

Valutazioni

  • AA-Omniscience Accuracy18,4%#133
  • Humanity's Last Exam14,1%#119
  • Terminal-Bench 4.05,1%#64
  • AA-LCR79,7%#51
  • SciCode39%#109
  • CritPt0%#143
  • MMMU-Pro74,2%#52
  • GPQA Diamond84,6%#51
  • τ²-Bench Banking47,4%#5
Qwen3.8 27B (Medium)Mediana
Dati di Artificial Analysis

Velocità e prezzo

Velocità

token al secondo · #147 su 162
  1. 5252Qwen3.8-Flash-Next
  2. 5151Granite 4.2 3B
  3. 5151GPT-6.1 Sol (Medium)
  4. 5050Qwen3.8 27B (Non-reasoning)
  5. 4949Qwen3.8 27B (Low)
  6. 4848Qwen3.8 27B (Medium)
  7. 4848Granite 4.2 30B
  8. 4646Phi-4 Mini Instruct
  9. 4545Gemma 4 E4B (Reasoning)
  10. 4545Qwen3.8 27B (Xhigh)
Dati di Artificial Analysis

Latenza

secondi al primo token · #117 su 162
  1. 3,73,7Ring-2.6-1T
  2. 3,83,8MiMo-V2.6-Flash
  3. 3,93,9Qwen3.8 27B (Xhigh)
  4. 3,93,9Qwen3.8 27B (Low)
  5. 44Qwen3.8 27B (Non-reasoning)
  6. 44Qwen3.8 27B (Medium)
  7. 44GPT-6.1 Sol (Medium)
  8. 5,15,1GPT-6 Astra (Medium)
  9. 5,25,2Claude Fable 5.1 (Medium)
  10. 6,26,2Claude Opus 5.5 (Low)
Dati di Artificial Analysis

Prezzo

$ per 1M token (3:1) · #100 su 169
  1. $0,850,85Nova 2.0 Lite (Non-reasoning)
  2. $0,980,98Apodex 1.1
  3. $1,11,1Qwen3.5 122B A10B (Non-reasoning)
  4. $1,11,1Qwen3.5 122B A10B (Reasoning)
  5. $1,131,13Qwen3.8 27B (Xhigh)
  6. $1,131,13Qwen3.8 27B (Medium)
  7. $1,131,13Qwen3.8 27B (Low)
  8. $1,131,13Nemotron 3 Ultra 550B A55B (Reasoning)
  9. $1,131,13Qwen3.8 27B (Non-reasoning)
  10. $1,31,3LongCat 2.0
Dati di Artificial Analysis

Modelli vicini

  • GPT-6 Luna (Medium)OpenAI29,9
  • Gemini 3.1 Pro PreviewGoogle29,7
  • Claude Haiku 5.5 (Low)Anthropic29,5
  • MiniMax-M3MiniMax29,2
  • Nex-N2-Pro (Based on Qwen3.5-397B-A17B)Nex AGI28,2
  • GPT-5.6 Terra (Low)OpenAI27,5
  • JT-4.1 Flash 236B A21B (Non-reasoning)China Mobile27,3
  • Quasar 438B (Max, Based on GLM-5.2)Multiverse Computing26,7
Dati di Artificial Analysis

Stesso laboratorio

  • 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 (Low)Alibaba26,2
  • Qwen3.7 PlusAlibaba25,2
  • Qwen3.5 397B A17B (Non-reasoning)Alibaba21,4
  • Qwen3.5 Omni PlusAlibaba20,4
Dati di Artificial Analysis
HorizonVascend IDEOlympusTalosCorsiCommunityBenchmark
DiscordGitHubXParliamoneNote legaliPrivacyCookieUso dei datiSicurezza
© 2026 Vascend Technologies · VAT IT04911550616
ascend