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

NVIDIA Nemotron 3 Nano 30B A3B (Reasoning)

  • NVIDIA
  • Open weights
  • Reasoning

Intelligence

Intelligence Index

#184 of 266
  1. 99gpt-oss-20b (High)
  2. 99Mistral Small 4 (Non-reasoning)
  3. 99K2-V2 (Medium)
  4. 99Tri-21B-Think
  5. 8.98.9Gemma 4 E4B (Reasoning)
  6. 8.98.9NVIDIA Nemotron 3 Nano 30B A3B (Reasoning)
  7. 8.88.8MiniCPM5-1B (Reasoning)
  8. 8.88.8Sarvam 105B (High)
  9. 8.78.7MiniCPM5-1B (Non-reasoning)
  10. 8.78.7Nova 2.0 Lite (Non-reasoning)
Data from Artificial Analysis

Evaluations

  • AA-Omniscience Accuracy17.3%#146
  • Humanity's Last Exam11.4%#137
  • Terminal-Bench 4.00%#96
  • AA-LCR38%#162
  • SciCode30.6%#125
  • CritPt0.9%#106
  • GPQA Diamond75.7%#89
  • IFBench71.1%#17
  • τ²-Bench Telecom40.9%#75
  • τ²-Bench Banking6%#81
  • Terminal-Bench Hard13.6%#48
NVIDIA Nemotron 3 Nano 30B A3B (Reasoning)Median
Data from Artificial Analysis

Speed and price

Speed

tokens per second · #12 of 162
  1. 353353Trinity Large Thinking
  2. 295295Nemotron 3.5 Lightning
  3. 290290Nova Micro
  4. 277277NVIDIA Nemotron 3 Nano 30B A3B (Non-reasoning)
  5. 265265gpt-oss-120b (Low)
  6. 241241NVIDIA Nemotron 3 Nano 30B A3B (Reasoning)
  7. 234234Claude Haiku 5.5 (Max)
  8. 233233gpt-oss-120b (High)
  9. 232232Qwen3.5 Omni Flash
  10. 231231Nemotron 3 Nano Omni 30B A3B Reasoning
Data from Artificial Analysis

Latency

seconds to first token · #37 of 162
  1. 0.90.9Qwen3.5 4B (Reasoning)
  2. 0.90.9Qwen3 Coder Next
  3. 0.90.9Mistral Small 4 (Non-reasoning)
  4. 11Gemma 4 26B A4B (Non-reasoning)
  5. 11gpt-oss-20b (Low)
  6. 11NVIDIA Nemotron 3 Nano 30B A3B (Reasoning)
  7. 11Ministral 3 14B
  8. 11Claude Sonnet 5.5 (Low)
  9. 11Llama 4 Maverick
  10. 11Nova 2.0 Pro Preview (Non-reasoning)
Data from Artificial Analysis

Price

$ per 1M tokens (3:1) · #16 of 169
  1. $0.060.06Qwen3.5 4B (Non-reasoning)
  2. $0.060.06Nova Micro
  3. $0.070.07NVIDIA Nemotron Nano 9B V2 (Reasoning)
  4. $0.070.07Sarvam 105B (High)
  5. $0.090.09NVIDIA Nemotron Nano 9B V2 (Non-reasoning)
  6. $0.090.09NVIDIA Nemotron 3 Nano 30B A3B (Reasoning)
  7. $0.090.09NVIDIA Nemotron 3 Nano 30B A3B (Non-reasoning)
  8. $0.090.09gpt-oss-20b (High)
  9. $0.10.1Nemotron 3.5 Lightning
  10. $0.10.1Ministral 3 3B
Data from Artificial Analysis

Nearby models

  • gpt-oss-20b (High)OpenAI9
  • Mistral Small 4 (Non-reasoning)Mistral9
  • K2-V2 (Medium)Institute of Foundation Models9
  • Tri-21B-ThinkTrillion Labs9
  • Gemma 4 E4B (Reasoning)Google8.9
  • MiniCPM5-1B (Reasoning)OpenBMB8.8
  • Sarvam 105B (High)Sarvam8.8
  • MiniCPM5-1B (Non-reasoning)OpenBMB8.7
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
  • Llama 3.1 Nemotron Ultra 253B v1 (Reasoning)NVIDIA7.5
  • NVIDIA Nemotron Nano 12B v2 VL (Reasoning)NVIDIA7.5
Data from Artificial Analysis
HorizonVascend IDEOlympusTalosCoursesCommunityBenchmark
DiscordGitHubXLet’s talkLegalPrivacyCookiesData useSecurity
© 2026 Vascend Technologies · VAT IT04911550616
ascend