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

Granite 4.2 30B

  • IBM
  • Release · August 25, 2026
  • Open weights
  • Reasoning

Intelligence

Intelligence Index

#139 of 266
  1. 13.113Qwen3.5 4B (Reasoning)
  2. 13.113Gemma 4 26B A4B (Non-reasoning)
  3. 13.113Command A+
  4. 12.913Nemotron 3.5 Lightning
  5. 12.813Nova 2.0 Pro Preview (Low)
  6. 12.713Granite 4.2 30B
  7. 12.513Nova 2.0 Lite (Medium)
  8. 12.513Qwen3.5 Omni Flash
  9. 12.513MiniCPM5-2B
  10. 12.312Mercury 2.5
Data from Artificial Analysis

Evaluations

  • AA-Omniscience Accuracy10.1%#218
  • Humanity's Last Exam11.2%#139
  • Terminal-Bench 4.00%#96
  • AA-LCR49%#148
  • SciCode37.9%#115
  • CritPt0.3%#117
  • GPQA Diamond64.4%#133
  • τ²-Bench Banking14.4%#61
Granite 4.2 30BMedian
Data from Artificial Analysis

Speed and price

Speed

tokens per second · #148 of 162
  1. 5151Granite 4.2 3B
  2. 5151GPT-6.1 Sol (Medium)
  3. 5050Qwen3.8 27B (Non-reasoning)
  4. 4949Qwen3.8 27B (Low)
  5. 4848Qwen3.8 27B (Medium)
  6. 4848Granite 4.2 30B
  7. 4646Phi-4 Mini Instruct
  8. 4545Gemma 4 E4B (Reasoning)
  9. 4545Qwen3.8 27B (Xhigh)
  10. 4545Gemma 4 E4B (Non-reasoning)
Data from Artificial Analysis

Latency

seconds to first token · #21 of 162
  1. 0.80.8gpt-oss-120b (High)
  2. 0.80.8Granite 4.2 8B
  3. 0.80.8Gemma 4 E4B (Non-reasoning)
  4. 0.80.8NVIDIA Nemotron 3 Nano 30B A3B (Non-reasoning)
  5. 0.80.8Nova Micro
  6. 0.80.8Granite 4.2 30B
  7. 0.80.8Nemotron 3 Nano Omni 30B A3B Reasoning
  8. 0.90.9Phi-4 Mini Instruct
  9. 0.90.9Ministral 3 8B
  10. 0.90.9Mistral Small 4 (Reasoning)
Data from Artificial Analysis

Price

$ per 1M tokens (3:1) · #60 of 169
  1. $0.260.26MiniMax-M3.1-Flash
  2. $0.260.26gpt-oss-120b (High)
  3. $0.260.26Mistral Small 4 (Reasoning)
  4. $0.260.26Mistral Small 4 (Non-reasoning)
  5. $0.280.28Qwen3.5 Omni Flash
  6. $0.280.28Granite 4.2 30B
  7. $0.30.3Llama 4 Scout
  8. $0.30.3NVIDIA Nemotron Nano 12B v2 VL (Non-reasoning)
  9. $0.310.31Nemotron 3.5 Super VL
  10. $0.330.33Celeris-1
Data from Artificial Analysis

Nearby models

  • Qwen3.5 4B (Reasoning)Alibaba13.1
  • Gemma 4 26B A4B (Non-reasoning)Google13.1
  • Command A+Cohere13.1
  • Nemotron 3.5 LightningNVIDIA12.9
  • Nova 2.0 Pro Preview (Low)Amazon12.8
  • Nova 2.0 Lite (Medium)Amazon12.5
  • Qwen3.5 Omni FlashAlibaba12.5
  • MiniCPM5-2BOpenBMB12.5
Data from Artificial Analysis

Same lab

  • Granite 4.2 8BIBM11.1
  • Granite 4.2 3BIBM9.1
  • Granite 4.0 H SmallIBM6
  • Granite 4.0 H 1BIBM5.2
  • 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