kanana-2-30B-a3B-thinking-2601: benchmark results
Provider: Kakao.
Aggregate Rating 1565 ± 26, rank #1476 of 10916 rated models, from 35 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Horangi 4 - KoBBQ | 93 | Accuracy (%) | 77.4 |
| Horangi 4 - BFCL | 67.83 | Accuracy (%) | 64.4 |
| Horangi 4 - Ko-TruthfulQA | 78 | Accuracy (%) | 42.3 |
| OrchestrationBench | 66.22 | Average Score | 37.5 |
| Horangi 4 - Ko-HellaSwag | 72 | Accuracy (%) | 36.1 |
| Horangi 4 - GLP - Specialized Knowledge | 36 | Score (%) | 35.6 |
| Horangi 4 - KMMLU-Pro | 62 | Accuracy (%) | 35.1 |
| Horangi 4 - HumanEval (100-problem subset) | 90 | Pass rate (%) | 34.6 |
| Horangi 4 - HRM8K | 78 | Accuracy (%) | 34.1 |
| Horangi 4 - Ko-AIME 2025 | 46.67 | Accuracy (%) | 34.1 |
| Horangi 4 - GLP - Mathematical Reasoning | 62.33 | Score (%) | 33.7 |
| Horangi 4 - KoBALT-700 (Syntax) | 43 | Accuracy (%) | 33.2 |
Interactive version: theaggregate.ai/model?slug=kanana-2-30b-a3b-thinking-2601 · How It Works · Data refreshed daily, snapshot 2026-11-08.