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

Nemotron Cascade 2 30B A3B

  • NVIDIA
  • Release · March 19, 2026
  • Open weights
  • Reasoning

Intelligence

Intelligence Index

#148 of 266
  1. 12.312Mercury 2.5
  2. 12.212JT-MINI
  3. 11.812Nova 2.0 Lite (Low)
  4. 11.812Magistral Medium 1.2
  5. 11.712HyperNova 60B 2605 (High, Based on gpt-oss-120b)
  6. 11.712Nemotron Cascade 2 30B A3B
  7. 11.612gpt-oss-120b (High)
  8. 11.512K2 Think V2
  9. 11.512LongCat Flash Lite
  10. 11.411HyperCLOVA X SEED Think (32B)
Data from Artificial Analysis

Evaluations

  • AA-Omniscience Accuracy18.3%#135
  • Humanity's Last Exam12%#130
  • AA-LCR39.3%#161
  • CritPt0.6%#112
  • GPQA Diamond75.8%#88
  • IFBench80.4%#3
  • τ²-Bench Telecom53.2%#62
  • Terminal-Bench Hard21.2%#34
Nemotron Cascade 2 30B A3BMedian
Data from Artificial Analysis

Nearby models

  • Mercury 2.5Inception12.3
  • JT-MINIChina Mobile12.2
  • Nova 2.0 Lite (Low)Amazon11.8
  • Magistral Medium 1.2Mistral11.8
  • HyperNova 60B 2605 (High, Based on gpt-oss-120b)Multiverse Computing11.7
  • gpt-oss-120b (High)OpenAI11.6
  • K2 Think V2Institute of Foundation Models11.5
  • LongCat Flash LiteLongCat11.5
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 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
  • 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