BenchLeader
IBMOpen weightsAuto-detected

Granite 4.0 1B

Best configuration ranks #567 of 610 on the BenchLeader Index at 37.2 ±3.6.

Blended price
Output speed
First answer
Context
128k
How it scores by categoryDashed line = average model (50). One step of 15 = one standard deviation.
  1. Overall index37
  2. Agents & tools34
  3. Knowledge25
  4. Instruction following26
  5. Long context28
  6. Composite35

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 index28.1%#500Artificial Analysis
Humanity's Last Exam (AA)not in index4.8%#392Artificial Analysis

Agents & tools

Knowledge

BenchmarkdefaultSource
AA-Omniscience-81.6#463Artificial Analysis

Instruction following

BenchmarkdefaultSource
IFBench20.5%#391Artificial Analysis

Long context

BenchmarkdefaultSource
AA-LCR6.0%#410Artificial Analysis

Composite

BenchmarkdefaultSource
AA Intelligence Index5.0#521Artificial Analysis

See also

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