Orion-14B-Chat: benchmark results
Provider: OrionStar. Released 2024-01-20. Access: Open.
Aggregate Rating 1409 ± 33, rank #5682 of 10916 rated models, from 10 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| LogicKor - Grammar | 5.85 | Score (0-10) | 64.7 |
| LogicKor - Writing | 7.5 | Score (0-10) | 50 |
| LogicKor - Reasoning | 5.71 | Score (0-10) | 48.7 |
| LogicKor - Multi-Turn | 5.76 | Score (0-10) | 46.4 |
| MAGI-Hard | 40.74 | Accuracy (%, 2024-05 snapshot) | 43.1 |
| LogicKor | 5.72 | Score (0-10) | 40.3 |
| LogicKor - Understanding | 6.71 | Score (0-10) | 35.1 |
| LogicKor - Single-Turn | 5.69 | Score (0-10) | 31.3 |
| LogicKor - Coding | 6 | Score (0-10) | 29 |
| LogicKor - Math | 2.57 | Score (0-10) | 20.8 |
Interactive version: theaggregate.ai/model?slug=orion-14b-chat · How It Works · Data refreshed daily, snapshot 2026-11-08.