Granite 4.2 8B

Composite indexes

• Artificial Analysis Intelligence Index#95 of 142
  11independentIntelligence Index v4.3; reasoningArtificial Analysis: Granite 4.2 8B ↗

  Leader: Claude Opus 5.5 at 58

Coding

• SciCode#87 of 94
  36.1%vendorthinkingHugging Face: ibm-granite/granite-4.2-30b model card ↗
  31.5%independentreasoningArtificial Analysis: Granite 4.2 8B ↗

  Leader: Claude Opus 5.5 at 66.9%

• Terminal-Bench 4.0#84 of 88
  0%independentreasoningArtificial Analysis: Granite 4.2 8B ↗

  Leader: Claude Mythos 5.1 at 60.9%

• Terminal-Bench 2.x#85 of 103
  20.6%vendorTerminal-Bench 2.1; thinkingHugging Face: ibm-granite/granite-4.2-30b model card ↗
  18.4%independentTerminal-Bench 2.1; reasoningArtificial Analysis: Granite 4.2 8B ↗

  Leader: Claude Fable 5.1 at 91.4%

• SWE-bench Pro#31 of 31
  19.1%vendorthinkingHugging Face: ibm-granite/granite-4.2-30b model card ↗

  Leader: Claude Opus 5.5 at 89.9%

• SWE-bench Verified#14 of 16
  47.7%vendorthinkingHugging Face: ibm-granite/granite-4.2-30b model card ↗

  Leader: Claude Sonnet 5 at 85.2%

• LiveCodeBench#19 of 56
  73.2%vendorv6; thinkingHugging Face: ibm-granite/granite-4.2-30b model card ↗

  Leader: Fugu at 92.9%

Agents and tool use

• GDPval-AA#77 of 103
  1189vendorGDPval (vendor-run)Hugging Face: ibm-granite/granite-4.2-30b model card ↗
  478independentreasoningArtificial Analysis: Granite 4.2 8B ↗

  Leader: Claude Opus 5.5 at 1846

Reasoning and knowledge

• GPQA Diamond#109 of 142
  64.1%vendorGPQA; thinkingHugging Face: ibm-granite/granite-4.2-30b model card ↗
  63.1%independentreasoningArtificial Analysis: Granite 4.2 8B ↗

  Leader: GPT-6 Astra at 96.1%

• Humanity’s Last Exam#107 of 147
  9.7%independentno tools; reasoningArtificial Analysis: Granite 4.2 8B ↗

  Leader: Claude Opus 5.5 at 61.4%

• CritPt#86 of 139
  0.3%independentreasoningArtificial Analysis: Granite 4.2 8B ↗

  Leader: GPT-5.6 Sol at 32.3%

• HMMT February 2026#7 of 8
  78.3%vendorHMMT Feb 2025 (not 2026); thinkingHugging Face: ibm-granite/granite-4.2-30b model card ↗

  Leader: GLM-5.2 at 92.5%

• MMLU-Pro#11 of 14
  74.0%vendorthinkingHugging Face: ibm-granite/granite-4.2-30b model card ↗

  Leader: Nemotron 3 Ultra 550B A55B at 86.8%

Vision and long context

• AA Long Context Reasoning#94 of 139
  45%independentreasoningArtificial Analysis: Granite 4.2 8B ↗

  Leader: Kimi K3 at 88.7%

Other published results