BenchLeader

Granite 4.1 3B

Best configuration ranks #532 of 610 on the BenchLeader Index at 39.3 ±3.7.

Blended price
Output speed
First answer
Context
131k
How it scores by categoryDashed line = average model (50). One step of 15 = one standard deviation.
  1. Overall index39
  2. Agents & tools36
  3. Knowledge28
  4. Instruction following37
  5. Long context28
  6. Composite36

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 index31.4%#486Artificial Analysis
Humanity's Last Exam (AA)not in index3.4%#510Artificial Analysis

Agents & tools

Knowledge

BenchmarkdefaultSource
AA-Omniscience-77.0#451Artificial Analysis

Instruction following

BenchmarkdefaultSource
IFBench33.7%#309Artificial Analysis

Long context

BenchmarkdefaultSource
AA-LCR6.0%#410Artificial Analysis

Composite

BenchmarkdefaultSource
AA Intelligence Index5.9#467Artificial Analysis

See also

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