Vascend
HorizonVascend IDEVascend CLICommunityBenchmarkContacto
AccederÚnete a Discord
InicioHorizonIDECLIAcceder
ChangelogInteligenciaCoste por tareaCoding Agent IndexCyber IndexDecision IndexBenchmarksVelocidadLatenciaPrecioClasificación
Benchmark

DeepSeek V4 Pro 0813 (Max)

  • DeepSeek
  • Lanzamiento · 13 de agosto de 2026
  • Pesos abiertos
  • Razonamiento

Inteligencia

Intelligence Index

#54 de 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)
Datos de Artificial Analysis

Evaluaciones

  • 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)Mediana
Datos de Artificial Analysis

Velocidad y precio

Velocidad

tokens por segundo · #87 de 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)
Datos de Artificial Analysis

Latencia

segundos al primer token · #65 de 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)
Datos de Artificial Analysis

Precio

$ por 1M tokens (3:1) · #116 de 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)
Datos de Artificial Analysis

Modelos cercanos

  • 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
Datos de Artificial Analysis

Mismo laboratorio

  • DeepSeek V4.1 Flash 1017 (Max)DeepSeek45,1
  • DeepSeek V4 Pro 0813 (Non-reasoning)DeepSeek20,4
Datos de Artificial Analysis
HorizonVascend IDEOlympusTalosCursosCommunityBenchmark
DiscordGitHubXHablemosAvisos legalesPrivacidadCookiesUso de datosSeguridad
© 2026 Vascend Technologies · VAT IT04911550616
ascend