Benchmark Almanac

nvidia-nemotron-nano-9b-v2

nvidia-nemotron-nano-9b-v2.

Released 18 Aug 2025
15
Benchmarks with a score
0
Ranked first, out of five or more models
0
In the top three
Unknown lab Aug 2025

nvidia-nemotron-nano-9b-v2

No Epoch Capabilities Index score yet
  • IFBench 34.6% #67 /70
  • CritPt 0% #141 /160
  • AgentIF (2026-10 setting) 61.2% #14 /24

Where it ranks

Its best score on each benchmark, and where that ranks among every model with a score there. We rank each model once, at its best setting.

Knowledge and language

BenchmarkScoreRankSource
IFEval 90.3% #22 of 126 Model card
AgentIF (2026-10 setting) 61.2% #14 of 24 Official leaderboard
RULER 78.9% #32 of 38 Model card
IFBench 34.6% #67 of 70 Model card
BullshitBench V2 5.00% #118 of 122 Official leaderboard
BullshitBench 7.27% #104 of 107 Official leaderboard
Humanity's Last Exam 6.50% #144 of 147 Model card
Fiction.LiveBench 25% #57 of 57 Epoch AI

Math and science

BenchmarkScoreRankSource
MATH-500 97.8% #11 of 67 Model card
AIME 2024 81.9% #34 of 87 Model card
GPQA Diamond 64% #199 of 284 Model card
AIME 2025 72.1% #108 of 143 Model card
CritPt 0% #141 of 160 Epoch AI

Coding

BenchmarkScoreRankSource
LiveCodeBench 71.1% #25 of 73 Model card

Agents and tools

BenchmarkScoreRankSource
Berkeley Function Calling Leaderboard (BFCL) 66.9% #30 of 47 Model card

Its launch post

The benchmarks the lab chose to headline, with the scores it gave.

Its system card

Every result in the longer documents the lab published with it. 2 of them aren't in the launch post.