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

KAT Coder Pro V2

  • KwaiKAT
  • Release · March 27, 2026
  • Proprietary
  • Non-reasoning

Intelligence

Intelligence Index

#98 of 266
  1. 24.124Solar Mini 4
  2. 22.923Nemotron 3 Ultra 550B A55B (Reasoning)
  3. 22.623Ling-3.0-flash-Fin
  4. 22.222Gemini 3.5 Flash-Lite
  5. 21.822G9v3-39A5B
  6. 21.722KAT Coder Pro V2
  7. 21.522GPT-6 Luna (Low)
  8. 21.522A.X-K2
  9. 21.421Qwen3.5 397B A17B (Non-reasoning)
  10. 21.421Nemotron 3.5 Bolt 74B-A9B
Data from Artificial Analysis

Evaluations

  • AA-Omniscience Accuracy21.5%#110
  • Humanity's Last Exam16.1%#113
  • AA-LCR73%#92
  • CritPt0%#143
  • GPQA Diamond85.5%#49
  • IFBench66.7%#23
  • τ²-Bench Telecom89.5%#15
  • τ²-Bench Banking4.5%#92
  • Terminal-Bench Hard49.2%#6
KAT Coder Pro V2Median
Data from Artificial Analysis

Nearby models

  • Solar Mini 4Upstage24.1
  • Nemotron 3 Ultra 550B A55B (Reasoning)NVIDIA22.9
  • Ling-3.0-flash-FinInclusionAI22.6
  • Gemini 3.5 Flash-LiteGoogle22.2
  • G9v3-39A5BAI9Stars21.8
  • GPT-6 Luna (Low)OpenAI21.5
  • A.X-K2SK Telecom21.5
  • Qwen3.5 397B A17B (Non-reasoning)Alibaba21.4
Data from Artificial Analysis
HorizonVascend IDEOlympusTalosCoursesCommunityBenchmark
DiscordGitHubXLet’s talkLegalPrivacyCookiesData useSecurity
© 2026 Vascend Technologies · VAT IT04911550616
ascend