Reasoning
No current rating
Mathematical and scientific problem solving.
Awaiting a qualified category score
Model profile / MBZUAI Institute of Foundation Models
K2 Horizon 0.9B. AA internal evaluated profile name retained; no scores inherited from intermediate or sibling checkpoints.
Four areas of evidence
Mathematical and scientific problem solving.
Software engineering and programming.
Factual reliability and instruction following.
Tool use, workflows and professional tasks.
Current index snapshot · 2026-09-16. Each category uses its own scale; scores across categories are not directly comparable. Evidence counts describe the retained Capabilities inputs; a family can contain several tasks or configurations. A point lead does not establish superiority.
Performance in context
K2 Horizon 0.9B is highlighted wherever a compatible measurement is available.
K2 Horizon 0.9B: No verified compatible standard first-party token quote for this exact release
Lumina Capabilities Index
The current Capabilities cohort, with this model highlighted.
Chart loads as you explore
K2 Horizon 0.9B: No exact published 10K single-request throughput for this release
Lumina Capabilities Index
The current Capabilities cohort, with this model highlighted.
Chart loads as you explore
Explore the detail
Connected, in range, at least three macro areas/four families; coverage tier meets the held-out support gate. Conditional on published execution and shared-factor assumptions. Conditional on recorded source settings; unknown execution dates remain unknown.
| Benchmark | Result | Published configuration | Source |
|---|---|---|---|
| No matching measurements. Try another search. | |||
No specialist task observations retained for this model.