readable AI benchmarks (simplified)
IBM
Granite 3.3 8B (Non-reasoning)
Granite 3.3 8B (Non-reasoning) has a Quality Score of 9.5, ranking 532nd among 551 scored models. Per 1M tokens, pricing is $0.030 input and $0.250 output. It has a 128k token context window. Its Reliability Score is 11.4, ranking 534th among 553 scored models, below average (total average: 35.6).
Quality Score9.5coverage 100.0%: AA Intelligence and AA-Omniscience outcomes available
Value Scorenot available
Factual reliability11.4
Cache Discountnot available
Model specification
- Reasoning
- non-reasoning
- Input modalities
- none
- Output modalities
- none
- Context window
- 128k tokens
- Weights
- open weights
Token prices USD per 1M tokens
- Input
- $0.030
- Output
- $0.250
- Cached Input
- not available
- Cache write
- not available
- Cost per task
- not available
Capability
- Intelligence
- 4.9
- Coding
- not available
- Agentic
- not available
- Omniscience
- -77.3
- Correct
- 9.7%
- Blended price
- not available
Answer outcomes
Fully graded outcomes (Correct + Incorrect): 96.6%
Correct 9.7%Incorrect 86.9%Partial / not attempted 3.4%
Artificial Analysis benchmarks
- Humanity’s Last Exam
- 4%
- GPQA Diamond
- 34%
- CritPt
- 0%
- AA-Omniscience
- 11%
Similar models
- Granite 4.0 MicroIBMQuality Score 9.5Value Score not available
- Granite 4.0 H 350MIBMQuality Score 8.5Value Score not available
- Granite 4.0 1BIBMQuality Score 8.5Value Score not available
- Granite 4.1 3BIBMQuality Score 10.3Value Score not available
- Granite 4.0 H 1BIBMQuality Score 10.9Value Score not available
- Granite 4.0 350MIBMQuality Score 11.4Value Score not available