BenchLeader
IBMOpen weightsAuto-detected

Granite 4.0 H 1B

Best configuration ranks #547 of 610 on the BenchLeader Index at 38.5 ±2.3.

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 index39
  2. Agents & tools34
  3. Knowledge30
  4. Instruction following31
  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 index26.3%#506Artificial Analysis
Humanity's Last Exam (AA)not in index5.0%#377Artificial Analysis

Agents & tools

Knowledge

BenchmarkdefaultSource
AA-Omniscience-72.3#445Artificial Analysis

Instruction following

BenchmarkdefaultSource
IFBench26.2%#369Artificial Analysis

Long context

BenchmarkdefaultSource
AA-LCR7.0%#404Artificial Analysis

Composite

BenchmarkdefaultSource
AA Intelligence Index5.2#509Artificial Analysis

See also

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