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

Granite 4.2 8B

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

Intelligence

Intelligence Index

#156 of 266
  1. 11.512LongCat Flash Lite
  2. 11.411HyperCLOVA X SEED Think (32B)
  3. 11.311Mistral Small 4 (Reasoning)
  4. 11.211Qwen3.5 9B (Reasoning)
  5. 11.211Qwen3 Next 80B A3B (Reasoning)
  6. 11.111Granite 4.2 8B
  7. 11.111Ling 3.0 Tiny
  8. 11.111Nova 2.0 Omni (Low)
  9. 1111Mi:dm K 2.5 Pro
  10. 10.811Trinity Large Thinking
Data from Artificial Analysis

Evaluations

  • AA-Omniscience Accuracy11.2%#211
  • Humanity's Last Exam9.7%#158
  • Terminal-Bench 4.00%#96
  • AA-LCR45%#153
  • SciCode31.5%#124
  • CritPt0.3%#117
  • GPQA Diamond63.1%#137
  • τ²-Bench Banking7.6%#73
Granite 4.2 8BMedian
Data from Artificial Analysis

Speed and price

Speed

tokens per second · #135 of 162
  1. 5757GPT-6 Astra (High)
  2. 5656Qwen3.7 Plus
  3. 5656MiMo-V2.6-Flash
  4. 5555Gemma 4 31B (Non-reasoning)
  5. 5555Claude Fable 5.1 (Medium)
  6. 5454Granite 4.2 8B
  7. 5353GPT-6.1 Sol (High)
  8. 5353GPT-6 Astra (Medium)
  9. 5353GPT-6.1 Sol (Xhigh)
  10. 5353GPT-6 Astra (Low)
Data from Artificial Analysis

Latency

seconds to first token · #17 of 162
  1. 0.80.8Qwen3 Next 80B A3B Instruct
  2. 0.80.8gpt-oss-20b (High)
  3. 0.80.8Llama 4 Scout
  4. 0.80.8Muse Spark Open (Xhigh)
  5. 0.80.8gpt-oss-120b (High)
  6. 0.80.8Granite 4.2 8B
  7. 0.80.8Gemma 4 E4B (Non-reasoning)
  8. 0.80.8NVIDIA Nemotron 3 Nano 30B A3B (Non-reasoning)
  9. 0.80.8Nova Micro
  10. 0.80.8Granite 4.2 30B
Data from Artificial Analysis

Price

$ per 1M tokens (3:1) · #21 of 169
  1. $0.090.09NVIDIA Nemotron 3 Nano 30B A3B (Reasoning)
  2. $0.090.09NVIDIA Nemotron 3 Nano 30B A3B (Non-reasoning)
  3. $0.090.09gpt-oss-20b (High)
  4. $0.10.1Nemotron 3.5 Lightning
  5. $0.10.1Ministral 3 3B
  6. $0.110.11Granite 4.2 8B
  7. $0.130.13Apertus 8B Instruct
  8. $0.130.13gpt-oss-20b (Low)
  9. $0.130.13Phi-4 Mini Instruct
  10. $0.140.14Phi-4 Multimodal Instruct
Data from Artificial Analysis

Nearby models

  • LongCat Flash LiteLongCat11.5
  • HyperCLOVA X SEED Think (32B)Naver11.4
  • Mistral Small 4 (Reasoning)Mistral11.3
  • Qwen3.5 9B (Reasoning)Alibaba11.2
  • Qwen3 Next 80B A3B (Reasoning)Alibaba11.2
  • Ling 3.0 TinyInclusionAI11.1
  • Nova 2.0 Omni (Low)Amazon11.1
  • Mi:dm K 2.5 ProKorea Telecom11
Data from Artificial Analysis

Same lab

  • Granite 4.2 30BIBM12.7
  • 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