reasoning benchmark
KINA
KINA is a knowledge-intensive evaluation that measures a model's breadth and depth of factual knowledge across academic and professional domains.
Updated Aug 7, 2026
Published models2
Registry coverage2
MetricScore
EvidenceB
KINA leaderboard
Sorted by the source-provided rank. Higher score is better according to the registry.
| 1 | BY | 48.3% | 100.0% | 2 | C | |
| 2 | BY | 46.6% | 0.0% | 2 | C |
Score distribution
Top published rows on the benchmark's original scale.
KINA highlights
The top published results on this benchmark's own scale.
What is KINA?
Definition and scoring fields from the benchmark registry.
KINA is a knowledge-intensive evaluation that measures a model's breadth and depth of factual knowledge across academic and professional domains.
Scores are shown in ratio. The current registry marks this benchmark as not independently verified with evidence level B.
- Family
- KINA
- Modality
- text
- Primary category
- reasoning
- Score direction
- higher
- LLMBoard eligible
- No
- Evaluation key
- kina|llm-stats-current
Source-native results are preserved. Eligibility for the overall LLMBoard score is a separate policy decision.
FAQ
Common questions about KINA.
Which model scores highest on KINA?
Seed 2.1 Pro is currently ranked first with 48.3%.
What does KINA measure?
KINA is a knowledge-intensive evaluation that measures a model's breadth and depth of factual knowledge across academic and professional domains.
Is a higher score better?
Yes. Higher values rank better for this benchmark.
How many models are compared?
2 unique published model results are currently shown.
Does this benchmark affect the overall score?
This benchmark is preserved as source-native evidence but is not eligible for the current overall score.