Vascend
HorizonVascend IDEVascend CLICommunityBenchmarkContatti
AccediEntra su Discord
HomeHorizonIDECLIAccedi
ChangelogIntelligenzaCosto per taskCoding Agent IndexCyber IndexDecision IndexBenchmarkVelocitàLatenzaPrezzoClassifica
Benchmark

Apertus 70B Instruct

  • Swiss AI Initiative
  • Rilascio · 2 settembre 2025
  • Pesi aperti
  • Senza ragionamento

Intelligenza

Intelligence Index

#256 su 266
  1. 5,25,2Olmo 3 7B Instruct
  2. 5,25,2Granite 4.0 H 1B
  3. 5,25,2Exaone 4.0 1.2B (Non-reasoning)
  4. 5,15,1Gemma 3 270M
  5. 5,15,1DeepHermes 3 - Llama-3.1 8B Preview (Non-reasoning)
  6. 5,15,1Apertus 70B Instruct
  7. 5,15,1Granite 4.0 Micro
  8. 55Molmo2-8B
  9. 4,84,8Granite 4.0 H 350M
  10. 4,84,8Granite 4.0 350M
Dati di Artificial Analysis

Valutazioni

  • AA-Omniscience Accuracy11,6%#207
  • Humanity's Last Exam5,5%#196
  • AA-LCR0%#229
  • CritPt0%#143
  • GPQA Diamond27,2%#204
  • IFBench25,9%#139
  • τ²-Bench Telecom12,9%#131
  • Terminal-Bench Hard0%#121
Apertus 70B InstructMediana
Dati di Artificial Analysis

Modelli vicini

  • Olmo 3 7B InstructAllen Institute for AI5,2
  • Granite 4.0 H 1BIBM5,2
  • Exaone 4.0 1.2B (Non-reasoning)LG AI Research5,2
  • Gemma 3 270MGoogle5,1
  • DeepHermes 3 - Llama-3.1 8B Preview (Non-reasoning)Nous Research5,1
  • Granite 4.0 MicroIBM5,1
  • Molmo2-8BAllen Institute for AI5
  • Granite 4.0 H 350MIBM4,8
Dati di Artificial Analysis

Stesso laboratorio

  • Apertus 8B InstructSwiss AI Initiative4,8
Dati di Artificial Analysis
HorizonVascend IDEOlympusTalosCorsiCommunityBenchmark
DiscordGitHubXParliamoneNote legaliPrivacyCookieUso dei datiSicurezza
© 2026 Vascend Technologies · VAT IT04911550616
ascend