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

Nova Premier

  • Amazon
  • Release · April 30, 2025
  • Proprietary
  • Non-reasoning

Intelligence

Intelligence Index

#177 of 266
  1. 9.510DiffusionGemma 26B A4B
  2. 9.49.4Gemma 4 12B (Non-reasoning)
  3. 9.39.3Llama 4 Maverick
  4. 9.29.2Qwen3 Coder Next
  5. 9.29.2Motif-2-12.7B-Reasoning
  6. 9.29.2Nova Premier
  7. 9.19.1Granite 4.2 3B
  8. 99gpt-oss-20b (High)
  9. 99Mistral Small 4 (Non-reasoning)
  10. 99K2-V2 (Medium)
Data from Artificial Analysis

Evaluations

  • AA-Omniscience Accuracy21.3%#111
  • Humanity's Last Exam4.2%#240
  • AA-LCR34.3%#171
  • CritPt0%#143
  • GPQA Diamond56.9%#154
  • IFBench36.2%#102
  • τ²-Bench Telecom38.3%#77
  • Terminal-Bench Hard6.8%#71
Nova PremierMedian
Data from Artificial Analysis

Nearby models

  • DiffusionGemma 26B A4BGoogle9.5
  • Gemma 4 12B (Non-reasoning)Google9.4
  • Llama 4 MaverickMeta9.3
  • Qwen3 Coder NextAlibaba9.2
  • Motif-2-12.7B-ReasoningMotif Technologies9.2
  • Granite 4.2 3BIBM9.1
  • gpt-oss-20b (High)OpenAI9
  • Mistral Small 4 (Non-reasoning)Mistral9
Data from Artificial Analysis

Same lab

  • Nova 2.0 Pro Preview (Medium)Amazon14.2
  • Nova 2.0 Omni (Medium)Amazon13.6
  • Nova 2.0 Lite (High)Amazon13.4
  • Nova 2.0 Pro Preview (Low)Amazon12.8
  • Nova 2.0 Lite (Medium)Amazon12.5
  • Nova 2.0 Lite (Low)Amazon11.8
  • Nova 2.0 Omni (Low)Amazon11.1
  • Nova 2.0 Pro Preview (Non-reasoning)Amazon10
Data from Artificial Analysis
HorizonVascend IDEOlympusTalosCoursesCommunityBenchmark
DiscordGitHubXLet’s talkLegalPrivacyCookiesData useSecurity
© 2026 Vascend Technologies · VAT IT04911550616
ascend