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

K2 Horizon 7B

  • Institute of Foundation Models
  • Release · September 3, 2026
  • Open weights
  • Reasoning

Intelligence

Intelligence Index

#104 of 266
  1. 21.522GPT-6 Luna (Low)
  2. 21.522A.X-K2
  3. 21.421Qwen3.5 397B A17B (Non-reasoning)
  4. 21.421Nemotron 3.5 Bolt 74B-A9B
  5. 20.821GPT-5.6 Terra (Non-reasoning)
  6. 20.621K2 Horizon 7B
  7. 20.420Qwen3.5 Omni Plus
  8. 20.420DeepSeek V4 Pro 0813 (Non-reasoning)
  9. 20.220o3
  10. 20.220Qwen3.8 27B (Non-reasoning)
Data from Artificial Analysis

Evaluations

  • AA-Omniscience Accuracy12.8%#200
  • Humanity's Last Exam18.2%#109
  • Terminal-Bench 4.01%#77
  • AA-LCR69.7%#108
  • SciCode27.6%#127
  • CritPt0.3%#117
  • GPQA Diamond75.3%#91
  • τ²-Bench Banking27.6%#35
K2 Horizon 7BMedian
Data from Artificial Analysis

Nearby models

  • GPT-6 Luna (Low)OpenAI21.5
  • A.X-K2SK Telecom21.5
  • Qwen3.5 397B A17B (Non-reasoning)Alibaba21.4
  • Nemotron 3.5 Bolt 74B-A9BNVIDIA21.4
  • GPT-5.6 Terra (Non-reasoning)OpenAI20.8
  • Qwen3.5 Omni PlusAlibaba20.4
  • DeepSeek V4 Pro 0813 (Non-reasoning)DeepSeek20.4
  • o3OpenAI20.2
Data from Artificial Analysis

Same lab

  • K2 Horizon 375B A23BInstitute of Foundation Models30.5
  • K2 Horizon MoVA 36B A4BInstitute of Foundation Models25.3
  • K2 Horizon 3.7BInstitute of Foundation Models15.6
  • K2 Think V2Institute of Foundation Models11.5
  • K2-V2 (High)Institute of Foundation Models9.9
  • K2-V2 (Medium)Institute of Foundation Models9
  • K2-V2 (Low)Institute of Foundation Models7.3
  • K2 Horizon 0.9BInstitute of Foundation Models3
Data from Artificial Analysis
HorizonVascend IDEOlympusTalosCoursesCommunityBenchmark
DiscordGitHubXLet’s talkLegalPrivacyCookiesData useSecurity
© 2026 Vascend Technologies · VAT IT04911550616
ascend