readable AI benchmarks (simplified)
IBM
Granite 4.2 3B
Granite 4.2 3B has a Quality Score of 28.3, ranking 217th among 398 scored models. Per 1M tokens, pricing is $0.030 input, $0.120 output, and $0.0075 cached input. It has a 131,072 token context window. Its Reliability Score is 42.6, ranking 173rd among 399 scored models, above average (total average: 38.0). Its Value Score is 27.4, low compared with the total Value average of 33.2.
Quality Score28.3coverage 100.0%: AA Intelligence and AA-Omniscience outcomes available
Value Score27.4
Factual reliability42.6
Cache Discount75%
Model specification
- Reasoning
- reasoning
- Input modalities
- none
- Output modalities
- none
- Context window
- 131,072 tokens
- Weights
- open weights
Token prices USD per 1M tokens
- Input
- $0.030
- Output
- $0.120
- Cached Input
- $0.0075
- Cache write
- not available
- Cost per task
- $0.0060
Capability
- Intelligence
- 9.1
- Coding
- not available
- Agentic
- not available
- Omniscience
- -14.7
- Correct
- 9.2%
- Blended price
- $0.023
Answer outcomes
Fully graded outcomes (Correct + Incorrect): 33.1%
Correct 9.2%Incorrect 23.9%Partial / not attempted 66.9%
Similar models
- Granite 4.2 8BIBMQuality Score 29.2Value Score 27.5
- Granite 4.2 30BIBMQuality Score 31.5Value Score 27.8
- Granite 4.0 H SmallIBMQuality Score 14.4Value Score not available
- Granite 4.0 350MIBMQuality Score 11.4Value Score not available
- Granite 4.0 H 1BIBMQuality Score 10.9Value Score not available
- Granite 4.0 MicroIBMQuality Score 9.5Value Score not available