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

NVIDIA Nemotron 3 Nano 4B

  • NVIDIA
  • Release · March 16, 2026
  • Open weights
  • Reasoning

Intelligence

Intelligence Index

#261 of 266
  1. 5.15.1Apertus 70B Instruct
  2. 5.15.1Granite 4.0 Micro
  3. 55Molmo2-8B
  4. 4.84.8Granite 4.0 H 350M
  5. 4.84.8Granite 4.0 350M
  6. 4.84.8NVIDIA Nemotron 3 Nano 4B
  7. 4.84.8Ministral 3 3B
  8. 4.84.8Tiny Aya Global
  9. 4.84.8Apertus 8B Instruct
  10. 4.84.8LFM2.5-VL-1.6B
Data from Artificial Analysis

Evaluations

  • AA-Omniscience Accuracy9.6%#223
  • Humanity's Last Exam4.9%#217
  • Terminal-Bench 4.00%#96
  • AA-LCR21.7%#190
  • SciCode16.1%#137
  • CritPt0%#143
  • GPQA Diamond51.3%#168
  • IFBench58.2%#44
  • τ²-Bench Telecom28.1%#82
  • Terminal-Bench Hard6.8%#71
NVIDIA Nemotron 3 Nano 4BMedian
Data from Artificial Analysis

Nearby models

  • Apertus 70B InstructSwiss AI Initiative5.1
  • Granite 4.0 MicroIBM5.1
  • Molmo2-8BAllen Institute for AI5
  • Granite 4.0 H 350MIBM4.8
  • Granite 4.0 350MIBM4.8
  • Ministral 3 3BMistral4.8
  • Tiny Aya GlobalCohere4.8
  • Apertus 8B InstructSwiss AI Initiative4.8
Data from Artificial Analysis

Same lab

  • Nemotron 3.5 Super VLNVIDIA26.5
  • Nemotron 3 Ultra 550B A55B (Reasoning)NVIDIA22.9
  • Nemotron 3.5 Bolt 74B-A9BNVIDIA21.4
  • Nemotron 3.5 LightningNVIDIA12.9
  • Nemotron Cascade 2 30B A3BNVIDIA11.7
  • Nemotron 3 Nano Omni 30B A3B ReasoningNVIDIA10.3
  • NVIDIA Nemotron 3 Nano 30B A3B (Reasoning)NVIDIA8.9
  • Llama 3.1 Nemotron Ultra 253B v1 (Reasoning)NVIDIA7.5
Data from Artificial Analysis
HorizonVascend IDEOlympusTalosCoursesCommunityBenchmark
DiscordGitHubXLet’s talkLegalPrivacyCookiesData useSecurity
© 2026 Vascend Technologies · VAT IT04911550616
ascend