Specifications
Context Window
—
Input Price/1M
—
Output Price/1M
—
Parameters
—
Benchmarks
K2-V2 (medium) results on the main AI model evaluation benchmarks. Higher scores indicate better performance.
Agentic
| Benchmark | Score | Maximum | Methodology |
|---|---|---|---|
| Terminal-Bench Hard | 10.0 | 100.0 | — |
Coding
| Benchmark | Score | Maximum | Methodology |
|---|---|---|---|
| LiveCodeBench | 69.0 | 100.0 | — |
| SciCode | 29.0 | 100.0 | — |
| AA Coding Index | 16.1 | 100.0 | — |
Knowledge
| Benchmark | Score | Maximum | Methodology |
|---|---|---|---|
| MMLU-Pro | 79.0 | 100.0 | — |
Long Context
| Benchmark | Score | Maximum | Methodology |
|---|---|---|---|
| AA-LCR | 33.0 | 100.0 | — |
Math
| Benchmark | Score | Maximum | Methodology |
|---|---|---|---|
| AA Math Index | 78.3 | 100.0 | — |
| AIME 2025 | 78.0 | 100.0 | — |
overall
| Benchmark | Score | Maximum | Methodology |
|---|---|---|---|
| AA Intelligence Index | 20.6 | 100.0 | — |
Reasoning
| Benchmark | Score | Maximum | Methodology |
|---|---|---|---|
| GPQA Diamond | 68.0 | 100.0 | — |
| IFBench | 60.0 | 100.0 | — |
| HLE | 10.0 | 100.0 | — |
Tool Use
| Benchmark | Score | Maximum | Methodology |
|---|---|---|---|
| Tau²-Bench | 28.0 | 100.0 | — |
Information
- Release date
- December 05, 2025
- Tool Calling
- ❌ Not supported
- Vision
- ❌ Not supported
- Audio
- ❌ Not supported
Full Analysis: K2-V2 (medium)
What is K2-V2 (medium)?
K2-V2 (medium) is an AI model developed by MBZUAI Institute of Foundation Models, classified as a text model. It focuses on text processing and natural language generation. As a proprietary model, it is available via MBZUAI Institute of Foundation Models's cloud API.
Pricing & Costs in 2026
K2-V2 (medium) does not have public per-token pricing available at this time. Some models offer access via enterprise plans or research programs. Check MBZUAI Institute of Foundation Models's official website for up-to-date availability and pricing.
Benchmarks & Performance
K2-V2 (medium) was evaluated on 13 different benchmarks, covering categories like Agentic, Coding, Knowledge, Long Context, Math, overall, Reasoning, Tool Use. Results show moderate performance across available evaluations.
It's important to note that benchmarks measure specific aspects and don't capture the full user experience. Factors like instruction adherence, behavior in long conversations, and real-world task quality vary significantly between models and aren't always reflected in standard scores.
Recommended Use Cases
K2-V2 (medium) specializes in text, offering advanced capabilities for creating and processing text content.
Comparison with Alternatives
In the 2026 AI model ecosystem, K2-V2 (medium) competes directly with similarly capable models. MBZUAI Institute of Foundation Models competes in this segment against OpenAI, Anthropic, Google, and Meta. The choice between models depends on the specific use case, budget, latency requirements, and need for features like multimodality and tool calling.
For a detailed side-by-side comparison, use our comparison tool or check the overall model ranking.
Frequently Asked Questions
What is K2-V2 (medium)?
K2-V2 (medium) is an AI model developed by MBZUAI Institute of Foundation Models. It is a text model.
How much does K2-V2 (medium) cost?
K2-V2 (medium) does not have public per-token pricing available at this time. Check MBZUAI Institute of Foundation Models's official website for up-to-date information.
How does K2-V2 (medium) compare with other models?
In available benchmarks, K2-V2 (medium) scored: Terminal-Bench Hard: 10/100, LiveCodeBench: 69/100, SciCode: 29/100. See the full table above for a detailed comparison.
Is K2-V2 (medium) open source?
No, K2-V2 (medium) is a proprietary model from MBZUAI Institute of Foundation Models. It is available via cloud API. For open source alternatives, check our open source model ranking.
What is K2-V2 (medium) best for?
K2-V2 (medium) excels at general-purpose language tasks.
Last updated: June 01, 2026 • View methodology →