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

Nanbeige4.1-3B

  • Nanbeige
  • Release · February 11, 2026
  • Open weights
  • Reasoning

Intelligence

Intelligence Index

#190 of 266
  1. 8.88.8MiniCPM5-1B (Reasoning)
  2. 8.88.8Sarvam 105B (High)
  3. 8.78.7MiniCPM5-1B (Non-reasoning)
  4. 8.78.7Nova 2.0 Lite (Non-reasoning)
  5. 8.68.6Magistral Small 1.2
  6. 8.48.4Nanbeige4.1-3B
  7. 8.48.4LFM2.5-2.6B
  8. 8.28.2EXAONE 4.0 32B (Reasoning)
  9. 8.28.2Nova 2.0 Omni (Non-reasoning)
  10. 7.97.9Hermes 4 - Llama-3.1 70B (Reasoning)
Data from Artificial Analysis

Evaluations

  • AA-Omniscience Accuracy9.9%#220
  • Humanity's Last Exam10.9%#144
  • AA-LCR0%#229
  • CritPt0%#143
  • GPQA Diamond85%#50
  • IFBench35.4%#104
  • τ²-Bench Telecom21.6%#101
  • Terminal-Bench Hard0%#121
Nanbeige4.1-3BMedian
Data from Artificial Analysis

Nearby models

  • MiniCPM5-1B (Reasoning)OpenBMB8.8
  • Sarvam 105B (High)Sarvam8.8
  • MiniCPM5-1B (Non-reasoning)OpenBMB8.7
  • Nova 2.0 Lite (Non-reasoning)Amazon8.7
  • Magistral Small 1.2Mistral8.6
  • LFM2.5-2.6BLiquid AI8.4
  • EXAONE 4.0 32B (Reasoning)LG AI Research8.2
  • Nova 2.0 Omni (Non-reasoning)Amazon8.2
Data from Artificial Analysis
HorizonVascend IDEOlympusTalosCoursesCommunityBenchmark
DiscordGitHubXLet’s talkLegalPrivacyCookiesData useSecurity
© 2026 Vascend Technologies · VAT IT04911550616
ascend