MBZUAIK2 Horizon 7B
K2 Horizon 7B is a MBZUAI open-weights reasoning model. It is not yet ranked: 3 independent results so far, and the index needs at least five across two categories.
- Blended price
- –
- Output speed
- –
- First answer
- –
- Context
- 524k
- Released
- –
- date not published by our sources
- Knowledge56
- Long context61
- Composite56
Benchmark results
One column per reasoning effort. Rank is among every configuration of every model on that benchmark. Hover a score for the run it came from.
Reasoning
| Benchmark | default | Source |
|---|---|---|
| GPQA Diamond (AA)not in index | 75.3%#244 | Artificial Analysis |
| Humanity's Last Exam (AA)not in index | 18.2%#180 | Artificial Analysis |
Coding
| Benchmark | default | Source |
|---|---|---|
| SciCode (AA)not in index | 27.6%#156 | Artificial Analysis |
Knowledge
| Benchmark | default | Source |
|---|---|---|
| AA-Omniscience | -16.6#173 | Artificial Analysis |
Long context
| Benchmark | default | Source |
|---|---|---|
| AA-LCR | 69.7%#173 | Artificial Analysis |
Composite
| Benchmark | default | Source |
|---|---|---|
| AA Intelligence Index | 21.1#169 | Artificial Analysis |
See also
Data as of 15 Sept 2026. Compare with another model.
Cite as: BenchLeader, “K2 Horizon 7B: benchmarks, pricing, speed and rank”, https://www.benchleader.com/models/k2-7b-ph2, data as of 15 Sept 2026.