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

JT-35B-Flash

  • China Mobile
  • Release · May 14, 2026
  • Proprietary
  • Non-reasoning

Intelligence

Intelligence Index

#111 of 266
  1. 20.420DeepSeek V4 Pro 0813 (Non-reasoning)
  2. 20.220o3
  3. 20.220Qwen3.8 27B (Non-reasoning)
  4. 19.720K-EXAONE 2.0 0803
  5. 19.119LongCat 2.0
  6. 18.719JT-35B-Flash
  7. 18.519GPT-6 Luna (Non-reasoning)
  8. 18.418Qwen3.5 397B A17B (Reasoning)
  9. 18.218Qwen3.6 35B A3B (Reasoning)
  10. 17.718Qwen3.5 122B A10B (Non-reasoning)
Data from Artificial Analysis

Evaluations

  • AA-Omniscience Accuracy24.2%#97
  • Humanity's Last Exam6.4%#181
  • AA-LCR65.7%#114
  • CritPt0%#143
  • GPQA Diamond82.9%#59
  • IFBench42%#80
  • τ²-Bench Telecom99.1%#1
  • Terminal-Bench Hard28.8%#22
JT-35B-FlashMedian
Data from Artificial Analysis

Nearby models

  • DeepSeek V4 Pro 0813 (Non-reasoning)DeepSeek20.4
  • o3OpenAI20.2
  • Qwen3.8 27B (Non-reasoning)Alibaba20.2
  • K-EXAONE 2.0 0803LG AI Research19.7
  • LongCat 2.0LongCat19.1
  • GPT-6 Luna (Non-reasoning)OpenAI18.5
  • Qwen3.5 397B A17B (Reasoning)Alibaba18.4
  • Qwen3.6 35B A3B (Reasoning)Alibaba18.2
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-MINIChina Mobile12.2
Data from Artificial Analysis
HorizonVascend IDEOlympusTalosCoursesCommunityBenchmark
DiscordGitHubXLet’s talkLegalPrivacyCookiesData useSecurity
© 2026 Vascend Technologies · VAT IT04911550616
ascend