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

Nemotron 3 Nano Omni 30B A3B Reasoning

  • NVIDIA
  • Release · April 29, 2026
  • Open weights
  • Reasoning

Intelligence

Intelligence Index

#165 of 266
  1. 10.811Trinity Large Thinking
  2. 10.811G9v3-3B
  3. 10.811Qwen3.5 4B (Non-reasoning)
  4. 10.611INTELLECT-3 (Based on GLM-4.5-Air)
  5. 10.410Solar Open 100B (Reasoning)
  6. 10.310Nemotron 3 Nano Omni 30B A3B Reasoning
  7. 10.210gpt-oss-120b (Low)
  8. 1010Nova 2.0 Pro Preview (Non-reasoning)
  9. 1010gpt-oss-20b (Low)
  10. 9.910North Mini Code
Data from Artificial Analysis

Evaluations

  • AA-Omniscience Accuracy15.2%#170
  • Humanity's Last Exam4.8%#220
  • AA-LCR39.7%#158
  • CritPt0%#143
  • MMMU-Pro53.2%#96
  • GPQA Diamond46.9%#174
  • IFBench63.2%#33
  • τ²-Bench Telecom45.3%#69
  • Terminal-Bench Hard8.3%#64
Nemotron 3 Nano Omni 30B A3B ReasoningMedian
Data from Artificial Analysis

Speed and price

Speed

tokens per second · #16 of 162
  1. 265265gpt-oss-120b (Low)
  2. 241241NVIDIA Nemotron 3 Nano 30B A3B (Reasoning)
  3. 234234Claude Haiku 5.5 (Max)
  4. 233233gpt-oss-120b (High)
  5. 232232Qwen3.5 Omni Flash
  6. 231231Nemotron 3 Nano Omni 30B A3B Reasoning
  7. 229229Step 5 Preview
  8. 223223Inkling Small
  9. 213213Ling 3.1 Flash
  10. 209209Ministral 3 3B
Data from Artificial Analysis

Latency

seconds to first token · #22 of 162
  1. 0.80.8Granite 4.2 8B
  2. 0.80.8Gemma 4 E4B (Non-reasoning)
  3. 0.80.8NVIDIA Nemotron 3 Nano 30B A3B (Non-reasoning)
  4. 0.80.8Nova Micro
  5. 0.80.8Granite 4.2 30B
  6. 0.80.8Nemotron 3 Nano Omni 30B A3B Reasoning
  7. 0.90.9Phi-4 Mini Instruct
  8. 0.90.9Ministral 3 8B
  9. 0.90.9Mistral Small 4 (Reasoning)
  10. 0.90.9GPT-6 Luna (Non-reasoning)
Data from Artificial Analysis

Price

$ per 1M tokens (3:1) · #83 of 169
  1. $0.530.53Solar Pro 4
  2. $0.530.53Inkling Small
  3. $0.530.53Muse Glimmer (High)
  4. $0.540.54MiMo-V2.6-Pro
  5. $0.60.6Beam 1.0
  6. $0.640.64Nemotron 3 Nano Omni 30B A3B Reasoning
  7. $0.660.66DeepSeek V4 Flash Vision (Max)
  8. $0.670.67Llama 3.3 Instruct 70B
  9. $0.70.7Qwen3.7 Plus
  10. $0.750.75Magistral Small 1.2
Data from Artificial Analysis

Nearby models

  • Trinity Large ThinkingArcee AI10.8
  • G9v3-3BAI9Stars10.8
  • Qwen3.5 4B (Non-reasoning)Alibaba10.8
  • INTELLECT-3 (Based on GLM-4.5-Air)Prime Intellect10.6
  • Solar Open 100B (Reasoning)Upstage10.4
  • gpt-oss-120b (Low)OpenAI10.2
  • Nova 2.0 Pro Preview (Non-reasoning)Amazon10
  • gpt-oss-20b (Low)OpenAI10
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
  • NVIDIA Nemotron 3 Nano 30B A3B (Reasoning)NVIDIA8.9
  • 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