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

G9v3-39A5B

  • AI9Stars
  • Release · August 20, 2026
  • Open weights
  • Reasoning

Intelligence

Intelligence Index

#97 of 266
  1. 24.625Ling-3.0-flash-VL
  2. 24.124Solar Mini 4
  3. 22.923Nemotron 3 Ultra 550B A55B (Reasoning)
  4. 22.623Ling-3.0-flash-Fin
  5. 22.222Gemini 3.5 Flash-Lite
  6. 21.822G9v3-39A5B
  7. 21.722KAT Coder Pro V2
  8. 21.522GPT-6 Luna (Low)
  9. 21.522A.X-K2
  10. 21.421Qwen3.5 397B A17B (Non-reasoning)
Data from Artificial Analysis

Evaluations

  • AA-Omniscience Accuracy14.9%#177
  • Humanity's Last Exam17.5%#111
  • AA-LCR65.3%#116
  • SciCode36.8%#116
  • CritPt0.3%#117
  • GPQA Diamond80.5%#71
  • τ²-Bench Banking22.1%#41
G9v3-39A5BMedian
Data from Artificial Analysis

Nearby models

  • Ling-3.0-flash-VLInclusionAI24.6
  • Solar Mini 4Upstage24.1
  • Nemotron 3 Ultra 550B A55B (Reasoning)NVIDIA22.9
  • Ling-3.0-flash-FinInclusionAI22.6
  • Gemini 3.5 Flash-LiteGoogle22.2
  • KAT Coder Pro V2KwaiKAT21.7
  • GPT-6 Luna (Low)OpenAI21.5
  • A.X-K2SK Telecom21.5
Data from Artificial Analysis

Same lab

  • G9v3-3BAI9Stars10.8
Data from Artificial Analysis
HorizonVascend IDEOlympusTalosCoursesCommunityBenchmark
DiscordGitHubXLet’s talkLegalPrivacyCookiesData useSecurity
© 2026 Vascend Technologies · VAT IT04911550616
ascend