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

MiniCPM5-2B

  • OpenBMB
  • Release · September 7, 2026
  • Open weights
  • Reasoning

Intelligence

Intelligence Index

#142 of 266
  1. 12.913Nemotron 3.5 Lightning
  2. 12.813Nova 2.0 Pro Preview (Low)
  3. 12.713Granite 4.2 30B
  4. 12.513Nova 2.0 Lite (Medium)
  5. 12.513Qwen3.5 Omni Flash
  6. 12.513MiniCPM5-2B
  7. 12.312Mercury 2.5
  8. 12.212JT-MINI
  9. 11.812Nova 2.0 Lite (Low)
  10. 11.812Magistral Medium 1.2
Data from Artificial Analysis

Evaluations

  • AA-Omniscience Accuracy8.4%#233
  • Humanity's Last Exam8.9%#164
  • Terminal-Bench 4.00%#96
  • AA-LCR59.3%#134
  • SciCode26.3%#128
  • CritPt0.3%#117
  • GPQA Diamond70.2%#115
  • τ²-Bench Banking20.8%#44
MiniCPM5-2BMedian
Data from Artificial Analysis

Nearby models

  • Nemotron 3.5 LightningNVIDIA12.9
  • Nova 2.0 Pro Preview (Low)Amazon12.8
  • Granite 4.2 30BIBM12.7
  • Nova 2.0 Lite (Medium)Amazon12.5
  • Qwen3.5 Omni FlashAlibaba12.5
  • Mercury 2.5Inception12.3
  • JT-MINIChina Mobile12.2
  • Nova 2.0 Lite (Low)Amazon11.8
Data from Artificial Analysis

Same lab

  • MiniCPM5-1B (Reasoning)OpenBMB8.8
  • MiniCPM5-1B (Non-reasoning)OpenBMB8.7
  • MiniCPM-V 4.6 1.3BOpenBMB5.7
Data from Artificial Analysis
HorizonVascend IDEOlympusTalosCoursesCommunityBenchmark
DiscordGitHubXLet’s talkLegalPrivacyCookiesData useSecurity
© 2026 Vascend Technologies · VAT IT04911550616
ascend