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

DeepSeek V4 Pro 0813 (Non-reasoning)

  • DeepSeek
  • Offene Gewichte
  • Ohne Reasoning

Intelligenz

Intelligence Index

#106 von 266
  1. 21,421Qwen3.5 397B A17B (Non-reasoning)
  2. 21,421Nemotron 3.5 Bolt 74B-A9B
  3. 20,821GPT-5.6 Terra (Non-reasoning)
  4. 20,621K2 Horizon 7B
  5. 20,420Qwen3.5 Omni Plus
  6. 20,420DeepSeek V4 Pro 0813 (Non-reasoning)
  7. 20,220o3
  8. 20,220Qwen3.8 27B (Non-reasoning)
  9. 19,720K-EXAONE 2.0 0803
  10. 19,119LongCat 2.0
Daten von Artificial Analysis

Bewertungen

  • AA-Omniscience Accuracy41,5%#52
  • Humanity's Last Exam10,6%#149
  • Terminal-Bench 4.01,5%#72
  • AA-LCR50,7%#145
  • SciCode39,9%#106
  • CritPt0%#143
DeepSeek V4 Pro 0813 (Non-reasoning)Median
Daten von Artificial Analysis

Geschwindigkeit und Preis

Geschwindigkeit

Tokens pro Sekunde · #90 von 162
  1. 105105Claude Sonnet 5.5 (Low)
  2. 105105Muse Glimmer (High)
  3. 105105DeepSeek V4 Pro 0813 (Max)
  4. 103103MiniMax-M3
  5. 103103Qwen3 Omni 30B A3B (Reasoning)
  6. 100100DeepSeek V4 Pro 0813 (Non-reasoning)
  7. 9999GPT-5.3 Codex (Xhigh)
  8. 9898GLM-5.3 (Max)
  9. 9696Qwen3 Omni 30B A3B Instruct
  10. 9696Claude Opus 5.5 (Max)
Daten von Artificial Analysis

Latenz

Sekunden bis zum ersten Token · #67 von 162
  1. 1,61,6Inkling Small
  2. 1,61,6Sarvam 105B (High)
  3. 1,71,7Claude Fable 5.1 (Low)
  4. 1,81,8DeepSeek V4 Pro 0813 (Max)
  5. 1,81,8Llama 3.3 Instruct 70B
  6. 1,81,8DeepSeek V4 Pro 0813 (Non-reasoning)
  7. 1,81,8Mistral Large 4 Preview
  8. 1,81,8Inkling (Xhigh)
  9. 1,81,8Qwen3.5 Omni Flash
  10. 1,81,8Command A
Daten von Artificial Analysis

Preis

$ pro 1M Tokens (3:1) · #117 von 169
  1. $1,51,5Hermes 4 - Llama-3.1 405B (Reasoning)
  2. $1,51,5Hermes 4 - Llama-3.1 405B (Non-reasoning)
  3. $1,711,71Kimi K2.7 Code
  4. $1,761,76Inkling (Xhigh)
  5. $1,981,98DeepSeek V4 Pro 0813 (Max)
  6. $1,981,98DeepSeek V4 Pro 0813 (Non-reasoning)
  7. $22Muse Spark Open (Xhigh)
  8. $2,072,07Mistral Large 4 Preview
  9. $2,152,15GLM-5.3 (Max)
  10. $2,152,15GLM-5.3 (Low)
Daten von Artificial Analysis

Ähnliche Modelle

  • Qwen3.5 397B A17B (Non-reasoning)Alibaba21,4
  • Nemotron 3.5 Bolt 74B-A9BNVIDIA21,4
  • GPT-5.6 Terra (Non-reasoning)OpenAI20,8
  • K2 Horizon 7BInstitute of Foundation Models20,6
  • Qwen3.5 Omni PlusAlibaba20,4
  • o3OpenAI20,2
  • Qwen3.8 27B (Non-reasoning)Alibaba20,2
  • K-EXAONE 2.0 0803LG AI Research19,7
Daten von Artificial Analysis

Gleiches Labor

  • DeepSeek V4.1 Flash 1017 (Max)DeepSeek45,1
  • DeepSeek V4 Pro 0813 (Max)DeepSeek36
  • DeepSeek V4 Flash Vision (Max)DeepSeek34,8
Daten von Artificial Analysis
HorizonVascend IDEOlympusTalosKurseCommunityBenchmark
DiscordGitHubXKontaktRechtlichesDatenschutzCookiesDatennutzungSicherheit
© 2026 Vascend Technologies · VAT IT04911550616
ascend