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

Motif-2-12.7B-Reasoning

  • Motif Technologies
  • Proprietary
  • Reasoning

Intelligence

Intelligence Index

#176 of 266
  1. 9.610Qwen3 Next 80B A3B Instruct
  2. 9.510DiffusionGemma 26B A4B
  3. 9.49.4Gemma 4 12B (Non-reasoning)
  4. 9.39.3Llama 4 Maverick
  5. 9.29.2Qwen3 Coder Next
  6. 9.29.2Motif-2-12.7B-Reasoning
  7. 9.29.2Nova Premier
  8. 9.19.1Granite 4.2 3B
  9. 99gpt-oss-20b (High)
  10. 99Mistral Small 4 (Non-reasoning)
Data from Artificial Analysis

Evaluations

  • AA-Omniscience Accuracy15.2%#170
  • Humanity's Last Exam8.8%#165
  • AA-LCR14.7%#207
  • CritPt0%#143
  • GPQA Diamond69.5%#120
  • IFBench57%#49
  • τ²-Bench Telecom46.5%#68
  • Terminal-Bench Hard3.8%#90
Motif-2-12.7B-ReasoningMedian
Data from Artificial Analysis

Nearby models

  • Qwen3 Next 80B A3B InstructAlibaba9.6
  • DiffusionGemma 26B A4BGoogle9.5
  • Gemma 4 12B (Non-reasoning)Google9.4
  • Llama 4 MaverickMeta9.3
  • Qwen3 Coder NextAlibaba9.2
  • Nova PremierAmazon9.2
  • Granite 4.2 3BIBM9.1
  • gpt-oss-20b (High)OpenAI9
Data from Artificial Analysis

Same lab

  • Motif 3Motif Technologies33.6
Data from Artificial Analysis
HorizonVascend IDEOlympusTalosCoursesCommunityBenchmark
DiscordGitHubXLet’s talkLegalPrivacyCookiesData useSecurity
© 2026 Vascend Technologies · VAT IT04911550616
ascend