readable AI benchmarks (simplified)
Prime Intellect
INTELLECT-3 (Based on GLM-4.5-Air)
INTELLECT-3 (Based on GLM-4.5-Air) has a Quality Score of 20.4, ranking 396th among 572 scored models. It has a 131,100 token context window. Its Reliability Score is 24.6, ranking 407th among 574 scored models, below average (total average: 36.5).
Quality Score20.4coverage 100.0%: AA Intelligence and AA-Omniscience outcomes available
Value Scorenot available
Factual reliability24.6
Cache Discountnot available
Model specification
- Reasoning
- reasoning
- Input modalities
- none
- Output modalities
- none
- Context window
- 131,100 tokens
- Weights
- open weights
Token prices USD per 1M tokens
- Input
- not available
- Output
- not available
- Cached Input
- not available
- Cache write
- not available
- Cost per task
- not available
Capability
- Intelligence
- 10.6
- Coding
- not available
- Agentic
- not available
- Omniscience
- -50.9
- Correct
- 19.6%
- Blended price
- not available
Answer outcomes
Fully graded outcomes (Correct + Incorrect): 90.0%
Correct 19.6%Incorrect 70.4%Partial / not attempted 10.0%
Artificial Analysis benchmarks
- Humanity’s Last Exam
- 13%
- GPQA Diamond
- 76%
- CritPt
- 0%
- AA-Omniscience
- 25%
- AA-LCR
- 40%
Similar models
- Ring-1TInclusionAIQuality Score 20.7Value Score not available
- North Mini CodeCohereQuality Score 20.5Value Score not available
- HyperCLOVA X SEED Think (32B)NaverQuality Score 20.4Value Score not available
- Qwen3.5 9B (Reasoning)AlibabaQuality Score 20.2Value Score not available
- Qwen3 Next 80B A3B (Reasoning)AlibabaQuality Score 20.8Value Score not available
- HyperNova 60B 2605 (High, Based on gpt-oss-120b)Multiverse ComputingQuality Score 20.4Value Score not available