Vascend
HorizonVascend IDEVascend CLICommunityBenchmarkContact
Sign inJoin Discord
HomeHorizonIDECLISign in
ChangelogIntelligenceCost per taskCoding Agent IndexCyber IndexDecision IndexBenchmarksSpeedLatencyPriceLeaderboard
Benchmark

Granite 4.0 Micro

  • IBM
  • Release · September 22, 2025
  • Open weights
  • Non-reasoning

Intelligence

Intelligence Index

#257 of 266
  1. 5.25.2Granite 4.0 H 1B
  2. 5.25.2Exaone 4.0 1.2B (Non-reasoning)
  3. 5.15.1Gemma 3 270M
  4. 5.15.1DeepHermes 3 - Llama-3.1 8B Preview (Non-reasoning)
  5. 5.15.1Apertus 70B Instruct
  6. 5.15.1Granite 4.0 Micro
  7. 55Molmo2-8B
  8. 4.84.8Granite 4.0 H 350M
  9. 4.84.8Granite 4.0 350M
  10. 4.84.8NVIDIA Nemotron 3 Nano 4B
Data from Artificial Analysis

Evaluations

  • AA-Omniscience Accuracy9.3%#225
  • Humanity's Last Exam5%#210
  • AA-LCR7%#220
  • CritPt0%#143
  • GPQA Diamond33.6%#193
  • IFBench24.8%#142
  • τ²-Bench Telecom12.6%#132
  • Terminal-Bench Hard1.5%#108
Granite 4.0 MicroMedian
Data from Artificial Analysis

Nearby models

  • 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
  • Apertus 70B InstructSwiss AI Initiative5.1
  • Molmo2-8BAllen Institute for AI5
  • Granite 4.0 H 350MIBM4.8
  • Granite 4.0 350MIBM4.8
Data from Artificial Analysis

Same lab

  • Granite 4.2 30BIBM12.7
  • Granite 4.2 8BIBM11.1
  • Granite 4.2 3BIBM9.1
  • Granite 4.0 H SmallIBM6
Data from Artificial Analysis
HorizonVascend IDEOlympusTalosCoursesCommunityBenchmark
DiscordGitHubXLet’s talkLegalPrivacyCookiesData useSecurity
© 2026 Vascend Technologies · VAT IT04911550616
ascend