BenchLeader
NVIDIAOpen weightsReasoning modelAuto-detected

Nemotron 3 Nano 4B

Best configuration ranks #425 of 610 on the BenchLeader Index at 44.1 ±8.2.

Blended price
Output speed
First answer
Context
262k
How it scores by categoryDashed line = average model (50). One step of 15 = one standard deviation.
  1. Overall index44
  2. Agents & tools40
  3. Knowledge31
  4. Instruction following58
  5. Long context36
  6. Composite38

Benchmark results

One column per reasoning effort. Rank is among every configuration of every model on that benchmark. Hover a score for the run it came from.

Reasoning

BenchmarkdefaultSource
GPQA Diamond (AA)not in index51.3%#401Artificial Analysis
Humanity's Last Exam (AA)not in index4.9%#390Artificial Analysis

Agents & tools

Knowledge

BenchmarkdefaultSource
AA-Omniscience-70.5#438Artificial Analysis

Instruction following

BenchmarkdefaultSource
IFBench58.2%#130Artificial Analysis

Long context

BenchmarkdefaultSource
AA-LCR21.7%#353Artificial Analysis

Composite

BenchmarkdefaultSource
AA Intelligence Index7.4#399Artificial Analysis

See also

Data as of 9 Sept 2026. Compare with another model.