# Kanana-2 1.3B Instruct Benchmark Scores & Performance

> Kanana-2 1.3B Instruct by Kakao has 4 source-displayable benchmark rows but no public overall score. It remains unranked.

Canonical page: https://benchlm.ai/models/kanana-2-1-3b-instruct

Last updated: September 10, 2026

## Model Details

| Property | Value |
|----------|-------|
| Creator | Kakao |
| Source Type | Open Weight |
| Reasoning Type | Non-Reasoning |
| Context Window | 32K |
| Official model card | [Kakao Kanana-2 1.3B Instruct model card](https://huggingface.co/kakaocorp/kanana-2-1.3b-instruct) |
| Overall Score | Coming soon |
| Overall Rank | Unranked |

## Family & Coverage

- Family: Kanana 2
- Variant: 1-3b
- Benchmarks covered: 4 of 434
- Sibling models: [Kanana-2 3B Instruct](/models/kanana-2-3b-instruct)
- Coverage note: BenchLM currently has partial benchmark coverage for this model, so the overall score is conservative.

## Instruction Following Benchmarks

| Benchmark | Score |
|-----------|-------|
| [IFBench](/benchmarks/ifbench) | 34.7% |
| [IFEval](/benchmarks/ifeval) | 77.6% |

## Korean Benchmarks Benchmarks

| Benchmark | Score |
|-----------|-------|
| [KMMLU](/benchmarks/kmmlu) | 42.8% |

## Mathematics Benchmarks

| Benchmark | Score |
|-----------|-------|
| [MATH-500](/benchmarks/math-500) | 61.4% |

## Other Kakao Models

- [Kanana-2 3B Instruct](/models/kanana-2-3b-instruct) - Score: not computed
- [Kanana Essence](/models/kanana-essence) - Score: not computed
- [Kanana Flag](/models/kanana-flag) - Score: not computed
- [Kanana Nano](/models/kanana-nano) - Score: not computed