← Models

Model profile

Nvidia Nemotron Nano 9B V2

NVIDIAdeveloper
2025-08-12release date
#200 / 267overall rank
3eval lineages

Evidence summary

Nvidia Nemotron Nano 9B V2 has an estimated overall rank of #200; its 90% source-sensitivity interval is #14–#255. Its behavior-only rank is #199; company governance moves the combined estimate to #200. Published evidence spans 3 evals and 2 of 7 behavior components. Its strongest relative result is AA-Omniscience (hallucination_rate, #73 of 311); its weakest is BullshitBench v2 (clear_pushback_rate, #100 of 105).

Compare this model

Only models sharing at least one published sub-eval are listed.

Official and reference links

Published eval results

Rank is within that sub-eval. Black marks the observed result; the grey dot marks the value implied by the global rank. Values stay on each source’s native scale.

Eval / sub-evalRankValueDistributionBetterSource
AA-Omnisciencehallucination_rate#73 / 3110.6101↓ lowerSource ↗official
BullshitBench v2clear_pushback_rate#100 / 1050.04↑ higherSource ↗official
Cisco AI Defense Rolling Single-Turn Leaderboardsingle_turn_attack_success_rate#77 / 10559.27↓ lowerSource ↗official

Values evaluations

Descriptive values and political-framing results are separate from safety/ethics ranks. Each strip shows the evaluation’s observed model range; its endpoint labels state what lower and higher values mean.

UGI Political Values

DimensionValueDistribution
Political Lean-17.9
Government48.6
Diplomacy66.8
Economy43.1
Society57.1