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

INTELLECT-3 (Based on GLM-4.5-Air)

  • Prime Intellect
  • Release · November 27, 2025
  • Open weights
  • Reasoning

Intelligence

Intelligence Index

#163 of 266
  1. 11.111Nova 2.0 Omni (Low)
  2. 1111Mi:dm K 2.5 Pro
  3. 10.811Trinity Large Thinking
  4. 10.811G9v3-3B
  5. 10.811Qwen3.5 4B (Non-reasoning)
  6. 10.611INTELLECT-3 (Based on GLM-4.5-Air)
  7. 10.410Solar Open 100B (Reasoning)
  8. 10.310Nemotron 3 Nano Omni 30B A3B Reasoning
  9. 10.210gpt-oss-120b (Low)
  10. 1010Nova 2.0 Pro Preview (Non-reasoning)
Data from Artificial Analysis

Evaluations

  • AA-Omniscience Accuracy19.6%#117
  • Humanity's Last Exam13.1%#126
  • AA-LCR39.7%#158
  • CritPt0.3%#117
  • GPQA Diamond76.1%#84
  • IFBench34%#110
  • τ²-Bench Telecom26.6%#87
  • Terminal-Bench Hard9.1%#63
INTELLECT-3 (Based on GLM-4.5-Air)Median
Data from Artificial Analysis

Nearby models

  • Nova 2.0 Omni (Low)Amazon11.1
  • Mi:dm K 2.5 ProKorea Telecom11
  • Trinity Large ThinkingArcee AI10.8
  • G9v3-3BAI9Stars10.8
  • Qwen3.5 4B (Non-reasoning)Alibaba10.8
  • Solar Open 100B (Reasoning)Upstage10.4
  • Nemotron 3 Nano Omni 30B A3B ReasoningNVIDIA10.3
  • gpt-oss-120b (Low)OpenAI10.2
Data from Artificial Analysis
HorizonVascend IDEOlympusTalosCoursesCommunityBenchmark
DiscordGitHubXLet’s talkLegalPrivacyCookiesData useSecurity
© 2026 Vascend Technologies · VAT IT04911550616
ascend