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

Granite 4.0 H 1B

  • IBM
  • Lanzamiento · 28 de octubre de 2025
  • Pesos abiertos
  • Sin razonamiento

Inteligencia

Intelligence Index

#252 de 266
  1. 5,35,3Exaone 4.0 1.2B (Reasoning)
  2. 5,25,2LFM2.5-1.2B-Thinking
  3. 5,25,2LFM2.5-1.2B-Instruct
  4. 5,25,2Jamba 1.7 Mini
  5. 5,25,2Olmo 3 7B Instruct
  6. 5,25,2Granite 4.0 H 1B
  7. 5,25,2Exaone 4.0 1.2B (Non-reasoning)
  8. 5,15,1Gemma 3 270M
  9. 5,15,1DeepHermes 3 - Llama-3.1 8B Preview (Non-reasoning)
  10. 5,15,1Apertus 70B Instruct
Datos de Artificial Analysis

Evaluaciones

  • AA-Omniscience Accuracy5,2%#250
  • Humanity's Last Exam5%#210
  • AA-LCR7%#220
  • CritPt0%#143
  • GPQA Diamond26,3%#207
  • IFBench26,2%#138
  • τ²-Bench Telecom19,6%#111
  • Terminal-Bench Hard0%#121
Granite 4.0 H 1BMediana
Datos de Artificial Analysis

Modelos cercanos

  • Exaone 4.0 1.2B (Reasoning)LG AI Research5,3
  • LFM2.5-1.2B-ThinkingLiquid AI5,2
  • LFM2.5-1.2B-InstructLiquid AI5,2
  • Jamba 1.7 MiniAI21 Labs5,2
  • Olmo 3 7B InstructAllen Institute for AI5,2
  • 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
Datos de Artificial Analysis

Mismo laboratorio

  • Granite 4.2 30BIBM12,7
  • Granite 4.2 8BIBM11,1
  • Granite 4.2 3BIBM9,1
  • Granite 4.0 H SmallIBM6
  • Granite 4.0 MicroIBM5,1
  • Granite 4.0 H 350MIBM4,8
  • Granite 4.0 350MIBM4,8
Datos de Artificial Analysis
HorizonVascend IDEOlympusTalosCursosCommunityBenchmark
DiscordGitHubXHablemosAvisos legalesPrivacidadCookiesUso de datosSeguridad
© 2026 Vascend Technologies · VAT IT04911550616
ascend