MBZUAI Institute of Foundation Models
K2-V2 (low)
Quality Score12.0
Value Scorenot available
Reliability26.4
Cache Discountnot available
Model specification
- Reasoning
- reasoning
- Input modalities
- text
- Output modalities
- text
- Context window
- 512k 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
- 8.4
- Coding
- not available
- Agentic
- not available
- Omniscience
- -47.3
- Correct
- 16.3%
- Blended price
- not available
Answer outcomes
Correct 16.3%Incorrect 63.6%Abstained 20.1%
Artificial Analysis benchmarks
- SciCode
- 22%
- Humanity’s Last Exam
- 4%
- GPQA Diamond
- 54%
- CritPt
- 0%
- AA-Omniscience
- 26%
- AA-LCR
- 20%
Similar models
- K2-V2 (medium)MBZUAI Institute of Foundation ModelsQuality Score 14.1Value Score not available
- K2-V2 (high)MBZUAI Institute of Foundation ModelsQuality Score 14.2Value Score not available
- K2 Think V2MBZUAI Institute of Foundation ModelsQuality Score 18.6Value Score not available
- Olmo 3.1 32B ThinkAllen Institute for AIQuality Score 11.2Value Score 11.7
- NVIDIA Nemotron Nano 9B V2 (Reasoning)NVIDIAQuality Score 10.9Value Score 11.1
- LFM2.5-8B-A1BLiquid AIQuality Score 10.4Value Score 10.7