Institute of Foundation Models model product
K2 Horizon MoVA 36B A4B is a Mixture-of-Experts reasoning model with 36B total parameters and about 4B active parameters per token.
Updated Nov 11, 2026. Default version: K2 Horizon MoVA 36B-A4B
This profile uses the model's current scored version. Arena ratings and prices are shown separately.
Benchmark scores for K2 Horizon MoVA 36B-A4B.
Benchmark | Score | Rank | Participants | Percentile | Evidence | Evaluated |
|---|
| BenchmarkOmniScience (non-hallucination rate) | Score69.20% | Rank03 | Participants4 | Percentile33.33% | EvidenceC | Evaluated |
| BenchmarkOmniScience | Score18.80% | Rank06 | Participants10 | Percentile44.44% | EvidenceC | Evaluated |
| BenchmarkTau3 Banking | Score26.80% | Rank09 | Participants22 | Percentile61.90% | EvidenceC | Evaluated |
| BenchmarkCritPT | Score2.10% | Rank10 | Participants10 | Percentile0.00% | EvidenceC | Evaluated |
| BenchmarkAA-LCR | Score66.30% | Rank18 | Participants32 | Percentile45.16% | EvidenceC | Evaluated |
| BenchmarkSciCode | Score38.90% | Rank22 | Participants37 | Percentile41.67% | EvidenceC | Evaluated |
| BenchmarkTerminal-Bench 2.1 | Score58.60% | Rank43 | Participants56 | Percentile23.64% | EvidenceC | Evaluated |
| BenchmarkHumanity's Last Exam | Score25.20% | Rank68 | Participants118 | Percentile42.74% | EvidenceC | Evaluated |
| BenchmarkGPQA | Score80.80% | Rank106 | Participants265 | Percentile60.23% | EvidenceC | Evaluated |
Preference and agent-evaluation results for the default version.
The default version does not have a matching Arena result yet.
Official vendor API pricing appears first, followed by individual provider offers.
The default version has no current input or output token prices.
Official prices use only the vendor's configured official Provider and positive standard USD PAYG rates. Third-party offers remain explicitly labeled.
Provider-specific output speed and catalog latency for K2 Horizon MoVA 36B-A4B. Runtime does not affect the capability score.
No provider-specific speed or latency record is linked to the default version yet.
Output Speed is generated output tokens received per second. Catalog latency is reported separately from observed provider TTFT.
Technical details for the model's default version.
Available versions of this model. The score column identifies the version used in the overall ranking.
Version | Released | LLMBoard | Parameters | Context | Max output | Open weights | License |
|---|
| VersionK2 Horizon MoVA 36B-A4B | Released | LLMBoard49.44 | Parameters36B | ContextN/A | Max outputN/A | Open weightsYes | LicenseApache 2.0 |
Recommendations prioritize the same model type and family, then the closest LLMBoard score.
Key information about K2 Horizon MoVA 36B A4B and its available data.
Developed by Institute of Foundation Models, it uses Mixture-of-Value Attention (MoVA) and has a native 524,288-token context window. It accepts text and produces text.
Data as of 2026-11-10.
Common questions about K2 Horizon MoVA 36B A4B.
K2 Horizon MoVA 36B A4B's default version was released on Sep 3, 2026.
No official standard PAYG price is currently available for K2 Horizon MoVA 36B A4B.
K2 Horizon MoVA 36B A4B was created by Institute of Foundation Models.
A context window is not available for the default version.
Yes. The default version is marked as open weight under Apache 2.0.
No provider offering is currently linked to the default version.