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

Granite 4.2 30B

  • IBM
  • Veröffentlichung · 25. August 2026
  • Offene Gewichte
  • Reasoning

Intelligenz

Intelligence Index

#139 von 266
  1. 13,113Qwen3.5 4B (Reasoning)
  2. 13,113Gemma 4 26B A4B (Non-reasoning)
  3. 13,113Command A+
  4. 12,913Nemotron 3.5 Lightning
  5. 12,813Nova 2.0 Pro Preview (Low)
  6. 12,713Granite 4.2 30B
  7. 12,513Nova 2.0 Lite (Medium)
  8. 12,513Qwen3.5 Omni Flash
  9. 12,513MiniCPM5-2B
  10. 12,312Mercury 2.5
Daten von Artificial Analysis

Bewertungen

  • AA-Omniscience Accuracy10,1%#218
  • Humanity's Last Exam11,2%#139
  • Terminal-Bench 4.00%#96
  • AA-LCR49%#148
  • SciCode37,9%#115
  • CritPt0,3%#117
  • GPQA Diamond64,4%#133
  • τ²-Bench Banking14,4%#61
Granite 4.2 30BMedian
Daten von Artificial Analysis

Geschwindigkeit und Preis

Geschwindigkeit

Tokens pro Sekunde · #148 von 162
  1. 5151Granite 4.2 3B
  2. 5151GPT-6.1 Sol (Medium)
  3. 5050Qwen3.8 27B (Non-reasoning)
  4. 4949Qwen3.8 27B (Low)
  5. 4848Qwen3.8 27B (Medium)
  6. 4848Granite 4.2 30B
  7. 4646Phi-4 Mini Instruct
  8. 4545Gemma 4 E4B (Reasoning)
  9. 4545Qwen3.8 27B (Xhigh)
  10. 4545Gemma 4 E4B (Non-reasoning)
Daten von Artificial Analysis

Latenz

Sekunden bis zum ersten Token · #21 von 162
  1. 0,80,8gpt-oss-120b (High)
  2. 0,80,8Granite 4.2 8B
  3. 0,80,8Gemma 4 E4B (Non-reasoning)
  4. 0,80,8NVIDIA Nemotron 3 Nano 30B A3B (Non-reasoning)
  5. 0,80,8Nova Micro
  6. 0,80,8Granite 4.2 30B
  7. 0,80,8Nemotron 3 Nano Omni 30B A3B Reasoning
  8. 0,90,9Phi-4 Mini Instruct
  9. 0,90,9Ministral 3 8B
  10. 0,90,9Mistral Small 4 (Reasoning)
Daten von Artificial Analysis

Preis

$ pro 1M Tokens (3:1) · #60 von 169
  1. $0,260,26MiniMax-M3.1-Flash
  2. $0,260,26gpt-oss-120b (High)
  3. $0,260,26Mistral Small 4 (Reasoning)
  4. $0,260,26Mistral Small 4 (Non-reasoning)
  5. $0,280,28Qwen3.5 Omni Flash
  6. $0,280,28Granite 4.2 30B
  7. $0,30,3Llama 4 Scout
  8. $0,30,3NVIDIA Nemotron Nano 12B v2 VL (Non-reasoning)
  9. $0,310,31Nemotron 3.5 Super VL
  10. $0,330,33Celeris-1
Daten von Artificial Analysis

Ähnliche Modelle

  • Qwen3.5 4B (Reasoning)Alibaba13,1
  • Gemma 4 26B A4B (Non-reasoning)Google13,1
  • Command A+Cohere13,1
  • Nemotron 3.5 LightningNVIDIA12,9
  • Nova 2.0 Pro Preview (Low)Amazon12,8
  • Nova 2.0 Lite (Medium)Amazon12,5
  • Qwen3.5 Omni FlashAlibaba12,5
  • MiniCPM5-2BOpenBMB12,5
Daten von Artificial Analysis

Gleiches Labor

  • Granite 4.2 8BIBM11,1
  • Granite 4.2 3BIBM9,1
  • Granite 4.0 H SmallIBM6
  • Granite 4.0 H 1BIBM5,2
  • Granite 4.0 MicroIBM5,1
  • Granite 4.0 H 350MIBM4,8
  • Granite 4.0 350MIBM4,8
Daten von Artificial Analysis
HorizonVascend IDEOlympusTalosKurseCommunityBenchmark
DiscordGitHubXKontaktRechtlichesDatenschutzCookiesDatennutzungSicherheit
© 2026 Vascend Technologies · VAT IT04911550616
ascend