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

Apriel-v1.6-15B-Thinker

  • ServiceNow
  • Release · November 25, 2025
  • Open weights
  • Reasoning

Intelligence

Intelligence Index

#131 of 266
  1. 14.214Mistral Medium 3.5
  2. 14.214Gemma 4 12B (Reasoning)
  3. 13.914Gemma 4 31B (Non-reasoning)
  4. 13.614Nova 2.0 Omni (Medium)
  5. 13.413Nova 2.0 Lite (High)
  6. 13.413Apriel-v1.6-15B-Thinker
  7. 13.313Qwen3.5 9B (Non-reasoning)
  8. 13.213EXAONE 4.5 33B (Reasoning)
  9. 13.113Qwen3.5 4B (Reasoning)
  10. 13.113Gemma 4 26B A4B (Non-reasoning)
Data from Artificial Analysis

Evaluations

  • AA-Omniscience Accuracy17%#150
  • Humanity's Last Exam10.8%#146
  • CritPt0.3%#117
  • GPQA Diamond73.3%#105
  • IFBench69.1%#19
  • τ²-Bench Telecom69.3%#50
  • Terminal-Bench Hard14.4%#47
Apriel-v1.6-15B-ThinkerMedian
Data from Artificial Analysis

Nearby models

  • Mistral Medium 3.5Mistral14.2
  • Gemma 4 12B (Reasoning)Google14.2
  • Gemma 4 31B (Non-reasoning)Google13.9
  • Nova 2.0 Omni (Medium)Amazon13.6
  • Nova 2.0 Lite (High)Amazon13.4
  • Qwen3.5 9B (Non-reasoning)Alibaba13.3
  • EXAONE 4.5 33B (Reasoning)LG AI Research13.2
  • Qwen3.5 4B (Reasoning)Alibaba13.1
Data from Artificial Analysis
HorizonVascend IDEOlympusTalosCoursesCommunityBenchmark
DiscordGitHubXLet’s talkLegalPrivacyCookiesData useSecurity
© 2026 Vascend Technologies · VAT IT04911550616
ascend