HyperCLOVAX-SEED-Omni-8B: benchmark results
Provider: Naver. Access: API.
Aggregate Rating 1436 ± 34, rank #4367 of 10916 rated models, from 34 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Horangi 4 - Ko-HalluLens (Nonexistent Entities) | 69 | Refusal rate (%) | 39.4 |
| Horangi 4 - BFCL | 62.79 | Accuracy (%) | 26.2 |
| Horangi 4 - Ko-HellaSwag | 64 | Accuracy (%) | 21.2 |
| Horangi 4 - KMMLU | 64 | Accuracy (%) | 19.7 |
| Horangi 4 - Ko-HLE | 8 | Accuracy (%) | 18.8 |
| Horangi 4 - Ko-AIME 2025 | 16.67 | Accuracy (%) | 13.5 |
| Horangi 4 - GLP - Logical Reasoning | 67.56 | Score (%) | 12.5 |
| Horangi 4 - Ko-TruthfulQA | 55 | Accuracy (%) | 12.5 |
| Horangi 4 - ALT - Hallucination Prevention | 43.33 | Score (%) | 11.5 |
| Horangi 4 - GLP - Mathematical Reasoning | 34.33 | Score (%) | 11.5 |
| Horangi 4 - GLP - General Knowledge | 64.32 | Score (%) | 10.6 |
| Horangi 4 - Ko-Moral | 46 | Accuracy (%) | 10.6 |
Interactive version: theaggregate.ai/model?slug=hyperclovax-seed-omni-8b · How It Works · Data refreshed daily, snapshot 2026-11-08.