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

JT-MINI

  • China Mobile
  • Release · April 15, 2026
  • Proprietary
  • Non-reasoning

Intelligence

Intelligence Index

#144 of 266
  1. 12.713Granite 4.2 30B
  2. 12.513Nova 2.0 Lite (Medium)
  3. 12.513Qwen3.5 Omni Flash
  4. 12.513MiniCPM5-2B
  5. 12.312Mercury 2.5
  6. 12.212JT-MINI
  7. 11.812Nova 2.0 Lite (Low)
  8. 11.812Magistral Medium 1.2
  9. 11.712HyperNova 60B 2605 (High, Based on gpt-oss-120b)
  10. 11.712Nemotron Cascade 2 30B A3B
Data from Artificial Analysis

Evaluations

  • AA-Omniscience Accuracy14.2%#186
  • Humanity's Last Exam6.4%#181
  • AA-LCR13%#210
  • CritPt0%#143
  • GPQA Diamond67.6%#125
  • IFBench36.7%#99
  • τ²-Bench Telecom93%#7
  • Terminal-Bench Hard18.2%#37
JT-MINIMedian
Data from Artificial Analysis

Nearby models

  • Granite 4.2 30BIBM12.7
  • Nova 2.0 Lite (Medium)Amazon12.5
  • Qwen3.5 Omni FlashAlibaba12.5
  • MiniCPM5-2BOpenBMB12.5
  • Mercury 2.5Inception12.3
  • Nova 2.0 Lite (Low)Amazon11.8
  • Magistral Medium 1.2Mistral11.8
  • HyperNova 60B 2605 (High, Based on gpt-oss-120b)Multiverse Computing11.7
Data from Artificial Analysis

Same lab

  • JT-4.1 Flash 236B A21B (Reasoning)China Mobile33.9
  • JT-4.1 Flash 236B A21B (Non-reasoning)China Mobile27.3
  • JT-35B-FlashChina Mobile18.7
Data from Artificial Analysis
HorizonVascend IDEOlympusTalosCoursesCommunityBenchmark
DiscordGitHubXLet’s talkLegalPrivacyCookiesData useSecurity
© 2026 Vascend Technologies · VAT IT04911550616
ascend