MBZUAI Institute of Foundation Models
K2 Think V2
Quality Score18.6
Value Scorenot available
Reliability29.8
Cache Discountnot available
Model specification
- Reasoning
- reasoning
- Input modalities
- text
- Output modalities
- text
- Context window
- 262,144 tokens
- Weights
- open weights
Token prices USD per 1M tokens
- Input
- not available
- Output
- not available
- Cached Input
- not available
- Cached Output
- not available
- Cost per task
- not available
Capability
- Intelligence
- 17.4
- Coding
- 21.0
- Agentic
- not available
- Omniscience
- -40.3
- Correct
- 18.0%
- Blended price
- not available
Answer outcomes
Correct 18.0%Incorrect 58.3%Abstained 23.6%
Artificial Analysis benchmarks
- GDPval-AA v2
- 0%
- Terminal-Bench v2.1
- 15%
- SciCode
- 33%
- Humanity’s Last Exam
- 10%
- GPQA Diamond
- 71%
- CritPt
- 0%
- AA-Omniscience
- 30%
- AA-LCR
- 55%
Similar models
- K2-V2 (high)MBZUAI Institute of Foundation ModelsQuality Score 14.2Value Score not available
- K2-V2 (medium)MBZUAI Institute of Foundation ModelsQuality Score 14.1Value Score not available
- K2-V2 (low)MBZUAI Institute of Foundation ModelsQuality Score 12.0Value Score not available
- Nemotron Cascade 2 30B A3BNVIDIAQuality Score 17.8Value Score not available
- G9v3-3BAI9StarsQuality Score 19.4Value Score 17.4
- Trinity Large ThinkingArcee AIQuality Score 19.4Value Score 19.9