DianXin-V1-Chat: benchmark results
Provider: Other.
Aggregate Rating 1398 ± 41, rank #6219 of 10916 rated models, from 47 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| OpenCompass Language - Dialogue - Chinese (CompassBench 2409) | 46.5 | Score (%) | 55.2 |
| OpenCompass Language - Creation - Chinese (CompassBench 2409) | 43 | Score (%) | 51.7 |
| OpenCompass Knowledge - Social Science - Chinese (CompassBench 2409) | 75 | Score (%) | 43.1 |
| OpenCompass Language - Dialogue - English (CompassBench 2409) | 40.7 | Score (%) | 39.7 |
| OpenCompass Language - NLP - Chinese (CompassBench 2409) | 44.2 | Score (%) | 37.9 |
| OpenCompass Reasoning - Social - Chinese (CompassBench 2409) | 33.2 | Score (%) | 36.2 |
| OpenCompass Language - Creation - English (CompassBench 2409) | 40 | Score (%) | 34.5 |
| OpenCompass Knowledge - Humanities - Chinese (CompassBench 2409) | 50 | Score (%) | 29.3 |
| OpenCompass Knowledge - Humanities - English (CompassBench 2409) | 64.8 | Score (%) | 27.6 |
| OpenCompass Reasoning - Common Sense - Chinese (CompassBench 2409) | 31.8 | Score (%) | 27.6 |
| OpenCompass LLM - Instruction Following (CompassBench 2409) | 39.2 | Score (%) | 24.1 |
| OpenCompass Knowledge - Science - Chinese (CompassBench 2409) | 47.2 | Score (%) | 20.7 |
Interactive version: theaggregate.ai/model?slug=dianxin-v1-chat · How It Works · Data refreshed daily, snapshot 2026-11-08.