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

Motif 3

  • Motif Technologies
  • Release · August 12, 2026
  • Open weights
  • Reasoning

Intelligence

Intelligence Index

#64 of 266
  1. 34.535Claude Haiku 5.5 (Medium)
  2. 34.334GLM-5.3 (Low)
  3. 34.234GPT-5.6 Terra (High)
  4. 33.934JT-4.1 Flash 236B A21B (Reasoning)
  5. 33.734Qwen3.8 27B (Xhigh)
  6. 33.634Motif 3
  7. 33.534Gemini 3.8 Flash (Low)
  8. 32.933GPT-6 Luna (High)
  9. 32.533GPT-5.3 Codex (Xhigh)
  10. 30.531K2 Horizon 375B A23B
Data from Artificial Analysis

Evaluations

  • AA-Omniscience Accuracy30.1%#78
  • Humanity's Last Exam37%#60
  • AA-LCR76%#83
  • SciCode42.3%#95
  • CritPt6.6%#78
  • GPQA Diamond83.4%#58
  • τ²-Bench Banking35.3%#24
Motif 3Median
Data from Artificial Analysis

Nearby models

  • Claude Haiku 5.5 (Medium)Anthropic34.5
  • GLM-5.3 (Low)Z AI34.3
  • GPT-5.6 Terra (High)OpenAI34.2
  • JT-4.1 Flash 236B A21B (Reasoning)China Mobile33.9
  • Qwen3.8 27B (Xhigh)Alibaba33.7
  • Gemini 3.8 Flash (Low)Google33.5
  • GPT-6 Luna (High)OpenAI32.9
  • GPT-5.3 Codex (Xhigh)OpenAI32.5
Data from Artificial Analysis

Same lab

  • Motif-2-12.7B-ReasoningMotif Technologies9.2
Data from Artificial Analysis
HorizonVascend IDEOlympusTalosCoursesCommunityBenchmark
DiscordGitHubXLet’s talkLegalPrivacyCookiesData useSecurity
© 2026 Vascend Technologies · VAT IT04911550616
ascend