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

Hermes 4 - Llama-3.1 405B (Reasoning)

  • Nous Research
  • Offene Gewichte
  • Reasoning

Intelligenz

Intelligence Index

#204 von 266
  1. 7,77,7Llama 3.3 Instruct 70B
  2. 7,57,5Llama 3.1 Nemotron Ultra 253B v1 (Reasoning)
  3. 7,57,5ERNIE 4.5 300B A47B
  4. 7,57,5NVIDIA Nemotron Nano 12B v2 VL (Reasoning)
  5. 7,57,5Gemma 4 E4B (Non-reasoning)
  6. 7,57,5Hermes 4 - Llama-3.1 405B (Reasoning)
  7. 7,47,4Hermes 4 - Llama-3.1 405B (Non-reasoning)
  8. 7,47,4NVIDIA Nemotron Nano 9B V2 (Reasoning)
  9. 7,37,3K2-V2 (Low)
  10. 7,37,3Llama 3.1 Instruct 405B
Daten von Artificial Analysis

Bewertungen

  • AA-Omniscience Accuracy30,1%#78
  • Humanity's Last Exam10,9%#144
  • AA-LCR22,3%#188
  • CritPt0,3%#117
  • GPQA Diamond72,7%#109
  • IFBench32,7%#117
  • τ²-Bench Telecom22,2%#98
  • Terminal-Bench Hard11,4%#53
Hermes 4 - Llama-3.1 405B (Reasoning)Median
Daten von Artificial Analysis

Geschwindigkeit und Preis

Geschwindigkeit

Tokens pro Sekunde · #154 von 162
  1. 4646Phi-4 Mini Instruct
  2. 4545Gemma 4 E4B (Reasoning)
  3. 4545Qwen3.8 27B (Xhigh)
  4. 4545Gemma 4 E4B (Non-reasoning)
  5. 4343Hermes 4 - Llama-3.1 405B (Non-reasoning)
  6. 4343Hermes 4 - Llama-3.1 405B (Reasoning)
  7. 4141Qwen3.8 2.4T A95B
  8. 4040Qwen3.8 Max (0902)
  9. 3939Phi-4
  10. 3535Gemma 4 31B (Reasoning)
Daten von Artificial Analysis

Latenz

Sekunden bis zum ersten Token · #93 von 162
  1. 2,32,3Gemma 4 12B (Non-reasoning)
  2. 2,32,3Qwen3.5 122B A10B (Reasoning)
  3. 2,32,3Hermes 4 - Llama-3.1 405B (Non-reasoning)
  4. 2,32,3Qwen3.7 Plus
  5. 2,32,3Qwen3.5 122B A10B (Non-reasoning)
  6. 2,32,3Hermes 4 - Llama-3.1 405B (Reasoning)
  7. 2,32,3GPT-6 Astra (Low)
  8. 2,42,4Mistral Medium 3.5
  9. 2,42,4GLM-5.3 (Max)
  10. 2,52,5GPT-6 Luna (Low)
Daten von Artificial Analysis

Preis

$ pro 1M Tokens (3:1) · #112 von 169
  1. $1,431,43Step 5 Preview
  2. $1,51,5Gemini 3.8 Flash (High)
  3. $1,51,5Gemini 3.8 Flash (Medium)
  4. $1,51,5Gemini 3.8 Flash (Low)
  5. $1,51,5Qwen3.5 Omni Plus
  6. $1,51,5Hermes 4 - Llama-3.1 405B (Reasoning)
  7. $1,51,5Hermes 4 - Llama-3.1 405B (Non-reasoning)
  8. $1,711,71Kimi K2.7 Code
  9. $1,761,76Inkling (Xhigh)
  10. $1,981,98DeepSeek V4 Pro 0813 (Max)
Daten von Artificial Analysis

Ähnliche Modelle

  • Llama 3.3 Instruct 70BMeta7,7
  • Llama 3.1 Nemotron Ultra 253B v1 (Reasoning)NVIDIA7,5
  • ERNIE 4.5 300B A47BBaidu7,5
  • NVIDIA Nemotron Nano 12B v2 VL (Reasoning)NVIDIA7,5
  • Gemma 4 E4B (Non-reasoning)Google7,5
  • Hermes 4 - Llama-3.1 405B (Non-reasoning)Nous Research7,4
  • NVIDIA Nemotron Nano 9B V2 (Reasoning)NVIDIA7,4
  • K2-V2 (Low)Institute of Foundation Models7,3
Daten von Artificial Analysis

Gleiches Labor

  • Hermes 4 - Llama-3.1 70B (Reasoning)Nous Research7,9
  • Hermes 4 - Llama-3.1 70B (Non-reasoning)Nous Research6,7
  • DeepHermes 3 - Mistral 24B Preview (Non-reasoning)Nous Research6,1
  • DeepHermes 3 - Llama-3.1 8B Preview (Non-reasoning)Nous Research5,1
Daten von Artificial Analysis
HorizonVascend IDEOlympusTalosKurseCommunityBenchmark
DiscordGitHubXKontaktRechtlichesDatenschutzCookiesDatennutzungSicherheit
© 2026 Vascend Technologies · VAT IT04911550616
ascend