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

Granite 4.0 H 1B

  • IBM
  • Release · October 28, 2025
  • Open weights
  • Non-reasoning

Intelligence

Intelligence Index

#252 of 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
Data from Artificial Analysis

Evaluations

  • 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 1BMedian
Data from Artificial Analysis

Nearby models

  • 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
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
  • Granite 4.0 MicroIBM5.1
  • Granite 4.0 H 350MIBM4.8
  • Granite 4.0 350MIBM4.8
Data from Artificial Analysis
HorizonVascend IDEOlympusTalosCoursesCommunityBenchmark
DiscordGitHubXLet’s talkLegalPrivacyCookiesData useSecurity
© 2026 Vascend Technologies · VAT IT04911550616
ascend