kanana-2-30B-a3B-instruct-2601: benchmark results
Provider: Kakao.
Aggregate Rating 1513 ± 33, rank #2146 of 10916 rated models, from 34 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Horangi 4 - Ko-HalluLens (Nonexistent Entities) | 96 | Refusal rate (%) | 96.2 |
| Horangi 4 - BFCL | 68.22 | Accuracy (%) | 74.4 |
| Horangi 4 - ALT - Hallucination Prevention | 62.67 | Score (%) | 57.2 |
| Horangi 4 - BigCodeBench (100-task subset) | 49 | Pass rate (%) | 48.6 |
| Horangi 4 - HAE-RAE Bench (without Reading Comprehension) | 85.86 | Accuracy (%) | 46.6 |
| Horangi 4 - Ko-TruthfulQA | 78 | Accuracy (%) | 42.3 |
| Horangi 4 - IFEval-Ko | 82.5 | Instruction-following accuracy (%) | 41.3 |
| Dnotitia Korean LLM Leaderboard | 83 | Mean Item Score (%) | 39.7 |
| Horangi 4 - GLP - General Knowledge | 72.43 | Score (%) | 25 |
| Horangi 4 - KMMLU-Pro | 54 | Accuracy (%) | 24.5 |
| Horangi 4 - HRM8K | 70 | Accuracy (%) | 24 |
| Horangi 4 - KoBBQ | 74 | Accuracy (%) | 22.6 |
Interactive version: theaggregate.ai/model?slug=kanana-2-30b-a3b-instruct-2601 · How It Works · Data refreshed daily, snapshot 2026-11-08.