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

MiniCPM5-1B (Non-reasoning)

  • OpenBMB
  • Open weights
  • Non-reasoning

Intelligence

Intelligence Index

#187 of 266
  1. 99Tri-21B-Think
  2. 8.98.9Gemma 4 E4B (Reasoning)
  3. 8.98.9NVIDIA Nemotron 3 Nano 30B A3B (Reasoning)
  4. 8.88.8MiniCPM5-1B (Reasoning)
  5. 8.88.8Sarvam 105B (High)
  6. 8.78.7MiniCPM5-1B (Non-reasoning)
  7. 8.78.7Nova 2.0 Lite (Non-reasoning)
  8. 8.68.6Magistral Small 1.2
  9. 8.48.4Nanbeige4.1-3B
  10. 8.48.4LFM2.5-2.6B
Data from Artificial Analysis

Evaluations

  • AA-Omniscience Accuracy0.1%#259
  • Humanity's Last Exam4.5%#229
  • AA-LCR5%#227
  • CritPt0%#143
  • GPQA Diamond26.9%#206
  • IFBench35.2%#105
  • τ²-Bench Telecom82.5%#32
  • Terminal-Bench Hard0%#121
MiniCPM5-1B (Non-reasoning)Median
Data from Artificial Analysis

Nearby models

  • Tri-21B-ThinkTrillion Labs9
  • Gemma 4 E4B (Reasoning)Google8.9
  • NVIDIA Nemotron 3 Nano 30B A3B (Reasoning)NVIDIA8.9
  • MiniCPM5-1B (Reasoning)OpenBMB8.8
  • Sarvam 105B (High)Sarvam8.8
  • Nova 2.0 Lite (Non-reasoning)Amazon8.7
  • Magistral Small 1.2Mistral8.6
  • Nanbeige4.1-3BNanbeige8.4
Data from Artificial Analysis

Same lab

  • MiniCPM5-2BOpenBMB12.5
  • MiniCPM-V 4.6 1.3BOpenBMB5.7
Data from Artificial Analysis
HorizonVascend IDEOlympusTalosCoursesCommunityBenchmark
DiscordGitHubXLet’s talkLegalPrivacyCookiesData useSecurity
© 2026 Vascend Technologies · VAT IT04911550616
ascend