# Kanana-2 1.3B Instruct vs Kanana-2 3B Instruct

> Side-by-side benchmark comparison for Kanana-2 1.3B Instruct and Kanana-2 3B Instruct across agentic, coding, multimodal, knowledge, reasoning, multilingual, and math tasks.

- Canonical page: https://benchlm.ai/compare/kanana-2-1-3b-instruct-vs-kanana-2-3b-instruct
- Last updated: September 10, 2026

- Shared sourced benchmarks: 3
- HTML indexing: indexable
- Ranking lane: BenchAlign v5

## Quick Verdict

Evidence is too thin for a benchmark verdict: Kanana-2 1.3B Instruct and Kanana-2 3B Instruct share only 3 sourced benchmark rows.

## Summary

- Only 3 shared sourced benchmark rows are available. That is not enough for a broad capability verdict, so this mirror does not name an overall winner.

## Model Snapshot

| Property | Kanana-2 1.3B Instruct | Kanana-2 3B Instruct |
|----------|----------|----------|
| Creator | Kakao | Kakao |
| Type | Open Weight | Open Weight |
| Reasoning | Non-Reasoning | Non-Reasoning |
| Context | 32K | 32K |
| Independent public score (not head-to-head) | null | null |
| Benchmarks Covered | 3 | 3 |
| Pricing (input/output) | $0.00 / $0.00 | $0.00 / $0.00 |

## Category Breakdown

### Instruction Following

- Winner: Insufficient shared evidence
- Kanana-2 1.3B Instruct public-lane score: Coming soon
- Kanana-2 3B Instruct public-lane score: Coming soon

| Benchmark | Kanana-2 1.3B Instruct | Kanana-2 3B Instruct | Winner |
|-----------|-----------|-----------|--------|
| IFBench | 34.7% | 33.3% | Kanana-2 1.3B Instruct |
| IFEval | 77.6% | 81.0% | Kanana-2 3B Instruct |

### Mathematics

- Winner: Insufficient shared evidence
- Kanana-2 1.3B Instruct public-lane score: Coming soon
- Kanana-2 3B Instruct public-lane score: Coming soon

| Benchmark | Kanana-2 1.3B Instruct | Kanana-2 3B Instruct | Winner |
|-----------|-----------|-----------|--------|
| MATH-500 | 61.4% | 61.2% | Kanana-2 1.3B Instruct |

## FAQ

### Is there enough evidence to pick between Kanana-2 1.3B Instruct and Kanana-2 3B Instruct?

Not yet. The models share only 3 sourced benchmark rows, so this mirror reports the available measurements and metadata without naming a broad winner.

### What can I compare safely on this page?

Published pricing, context windows, model type, and individual shared benchmark rows are directly comparable. Independent overall scores and non-overlapping benchmark coverage are labeled separately and should not be read as a controlled head-to-head result.

## Related Comparisons

- [Kanana-2 1.3B Instruct vs Claude Fable 5.1](/compare/claude-fable-5-1-vs-kanana-2-1-3b-instruct)
- [Kanana-2 3B Instruct vs Claude Fable 5.1](/compare/claude-fable-5-1-vs-kanana-2-3b-instruct)
- [Kanana-2 1.3B Instruct vs GPT-6 Astra](/compare/gpt-6-astra-vs-kanana-2-1-3b-instruct)
- [Kanana-2 3B Instruct vs GPT-6 Astra](/compare/gpt-6-astra-vs-kanana-2-3b-instruct)

## Explore More

- [Kanana-2 1.3B Instruct profile](/models/kanana-2-1-3b-instruct)
- [Kanana-2 3B Instruct profile](/models/kanana-2-3b-instruct)
- [Compare Pricing](/llm-pricing)
- [Alternative Finder](/tools/alternative-finder)
- [LLM Selector](/tools/llm-selector)
- [Overall Rankings](/best/overall)