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

DeepSeek V4 Pro 0813 (Max)

  • DeepSeek
  • Veröffentlichung · 13. August 2026
  • Offene Gewichte
  • Reasoning

Intelligenz

Intelligence Index

#54 von 266
  1. 38,438Mistral Large 4 Preview
  2. 38,138GPT-6 Luna (Max)
  3. 3838GPT-5.6 Terra (Xhigh)
  4. 37,938MiMo-V2.6-Flash
  5. 37,838Claude Haiku 5.5 (High)
  6. 3636DeepSeek V4 Pro 0813 (Max)
  7. 35,936Claude Sonnet 5.5 (Low)
  8. 35,235Agnes 2.5 Pro Beta
  9. 34,835DeepSeek V4 Flash Vision (Max)
  10. 34,635GPT-6 Luna (Xhigh)
Daten von Artificial Analysis

Bewertungen

  • AA-Omniscience Accuracy49,1%#34
  • Humanity's Last Exam41%#48
  • Terminal-Bench 4.014,1%#53
  • AA-LCR80,3%#41
  • SciCode51%#58
  • CritPt18%#42
  • GPQA Diamond92,8%#13
  • τ²-Bench Banking39,6%#19
DeepSeek V4 Pro 0813 (Max)Median
Daten von Artificial Analysis

Geschwindigkeit und Preis

Geschwindigkeit

Tokens pro Sekunde · #87 von 162
  1. 108108Gemma 4 26B A4B (Non-reasoning)
  2. 106106Claude Sonnet 5.5 (Medium)
  3. 106106Claude Sonnet 5.5 (High)
  4. 105105Claude Sonnet 5.5 (Low)
  5. 105105Muse Glimmer (High)
  6. 105105DeepSeek V4 Pro 0813 (Max)
  7. 103103MiniMax-M3
  8. 103103Qwen3 Omni 30B A3B (Reasoning)
  9. 100100DeepSeek V4 Pro 0813 (Non-reasoning)
  10. 9999GPT-5.3 Codex (Xhigh)
Daten von Artificial Analysis

Latenz

Sekunden bis zum ersten Token · #65 von 162
  1. 1,51,5Magistral Small 1.2
  2. 1,61,6DeepSeek V4 Flash Vision (Max)
  3. 1,61,6Inkling Small
  4. 1,61,6Sarvam 105B (High)
  5. 1,71,7Claude Fable 5.1 (Low)
  6. 1,81,8DeepSeek V4 Pro 0813 (Max)
  7. 1,81,8Llama 3.3 Instruct 70B
  8. 1,81,8DeepSeek V4 Pro 0813 (Non-reasoning)
  9. 1,81,8Mistral Large 4 Preview
  10. 1,81,8Inkling (Xhigh)
Daten von Artificial Analysis

Preis

$ pro 1M Tokens (3:1) · #116 von 169
  1. $1,51,5Qwen3.5 Omni Plus
  2. $1,51,5Hermes 4 - Llama-3.1 405B (Reasoning)
  3. $1,51,5Hermes 4 - Llama-3.1 405B (Non-reasoning)
  4. $1,711,71Kimi K2.7 Code
  5. $1,761,76Inkling (Xhigh)
  6. $1,981,98DeepSeek V4 Pro 0813 (Max)
  7. $1,981,98DeepSeek V4 Pro 0813 (Non-reasoning)
  8. $22Muse Spark Open (Xhigh)
  9. $2,072,07Mistral Large 4 Preview
  10. $2,152,15GLM-5.3 (Max)
Daten von Artificial Analysis

Ähnliche Modelle

  • Mistral Large 4 PreviewMistral38,4
  • GPT-6 Luna (Max)OpenAI38,1
  • GPT-5.6 Terra (Xhigh)OpenAI38
  • MiMo-V2.6-FlashXiaomi37,9
  • Claude Haiku 5.5 (High)Anthropic37,8
  • Claude Sonnet 5.5 (Low)Anthropic35,9
  • Agnes 2.5 Pro BetaSapiens AI35,2
  • DeepSeek V4 Flash Vision (Max)DeepSeek34,8
Daten von Artificial Analysis

Gleiches Labor

  • DeepSeek V4.1 Flash 1017 (Max)DeepSeek45,1
  • DeepSeek V4 Pro 0813 (Non-reasoning)DeepSeek20,4
Daten von Artificial Analysis
HorizonVascend IDEOlympusTalosKurseCommunityBenchmark
DiscordGitHubXKontaktRechtlichesDatenschutzCookiesDatennutzungSicherheit
© 2026 Vascend Technologies · VAT IT04911550616
ascend