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

Agnes 2.5 Pro Beta

  • Sapiens AI
  • Veröffentlichung · 26. August 2026
  • Proprietär
  • Reasoning

Intelligenz

Intelligence Index

#56 von 266
  1. 3838GPT-5.6 Terra (Xhigh)
  2. 37,938MiMo-V2.6-Flash
  3. 37,838Claude Haiku 5.5 (High)
  4. 3636DeepSeek V4 Pro 0813 (Max)
  5. 35,936Claude Sonnet 5.5 (Low)
  6. 35,235Agnes 2.5 Pro Beta
  7. 34,835DeepSeek V4 Flash Vision (Max)
  8. 34,635GPT-6 Luna (Xhigh)
  9. 34,535Claude Haiku 5.5 (Medium)
  10. 34,334GLM-5.3 (Low)
Daten von Artificial Analysis

Bewertungen

  • AA-Omniscience Accuracy16,8%#152
  • Humanity's Last Exam37,5%#57
  • AA-LCR83%#18
  • SciCode48,8%#69
  • CritPt15,7%#53
  • MMMU-Pro75,4%#47
  • GPQA Diamond90,5%#24
  • τ²-Bench Banking35,7%#22
Agnes 2.5 Pro BetaMedian
Daten von Artificial Analysis

Geschwindigkeit und Preis

Geschwindigkeit

Tokens pro Sekunde · #77 von 162
  1. 116116GPT-6 Luna (Low)
  2. 116116GPT-5.6 Terra (Low)
  3. 115115Nova 2.0 Pro Preview (Non-reasoning)
  4. 114114GPT-5.6 Terra (Medium)
  5. 114114Gemma 4 12B (Reasoning)
  6. 114114Agnes 2.5 Pro Beta
  7. 113113MiniMax-M3.1-Flash
  8. 112112Solar Mini 4
  9. 109109Mistral Large 4 Preview
  10. 108108Claude Sonnet 5.5 (Xhigh)
Daten von Artificial Analysis

Latenz

Sekunden bis zum ersten Token · #57 von 162
  1. 1,31,3MiniMax-M3
  2. 1,31,3Llama 3.2 Instruct 11B (Vision)
  3. 1,41,4MiniMax-M3.1-Flash
  4. 1,41,4Claude Sonnet 5.5 (Medium)
  5. 1,41,4GPT-5.6 Terra (Low)
  6. 1,41,4Agnes 2.5 Pro Beta
  7. 1,41,4Reka Flash 3
  8. 1,51,5GPT-5.6 Terra (Medium)
  9. 1,51,5Magistral Small 1.2
  10. 1,61,6DeepSeek V4 Flash Vision (Max)
Daten von Artificial Analysis

Preis

$ pro 1M Tokens (3:1) · #26 von 169
  1. $0,110,11Granite 4.2 8B
  2. $0,130,13Apertus 8B Instruct
  3. $0,130,13gpt-oss-20b (Low)
  4. $0,130,13Phi-4 Mini Instruct
  5. $0,140,14Phi-4 Multimodal Instruct
  6. $0,150,15Agnes 2.5 Pro Beta
  7. $0,150,15Gemma 4 12B (Reasoning)
  8. $0,150,15Gemma 4 12B (Non-reasoning)
  9. $0,150,15Ministral 3 8B
  10. $0,150,15Qwen3.5 9B (Reasoning)
Daten von Artificial Analysis

Ähnliche Modelle

  • GPT-5.6 Terra (Xhigh)OpenAI38
  • MiMo-V2.6-FlashXiaomi37,9
  • Claude Haiku 5.5 (High)Anthropic37,8
  • DeepSeek V4 Pro 0813 (Max)DeepSeek36
  • Claude Sonnet 5.5 (Low)Anthropic35,9
  • DeepSeek V4 Flash Vision (Max)DeepSeek34,8
  • GPT-6 Luna (Xhigh)OpenAI34,6
  • Claude Haiku 5.5 (Medium)Anthropic34,5
Daten von Artificial Analysis
HorizonVascend IDEOlympusTalosKurseCommunityBenchmark
DiscordGitHubXKontaktRechtlichesDatenschutzCookiesDatennutzungSicherheit
© 2026 Vascend Technologies · VAT IT04911550616
ascend