SenseChat-V5-0522: benchmark results
Provider: Other.
Aggregate Rating 1574 ± 22, rank #1332 of 10916 rated models, from 65 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| OpenCompass Agent - T-Eval - Chinese (CompassBench 2404) | 85.2 | Score (%) | 100 |
| OpenCompass Agent - T-Eval - English (CompassBench 2404) | 86.7 | Score (%) | 100 |
| OpenCompass Code - HumanEval+ - English (CompassBench 2404) | 70.7 | Score (%) | 100 |
| OpenCompass LLM - Knowledge (CompassBench 2404) | 72.5 | Score (%) | 100 |
| OpenCompass LLM - Knowledge - English (CompassBench 2404) | 81 | Score (%) | 100 |
| OpenCompass LLM - Reasoning (CompassBench 2404) | 51.2 | Score (%) | 100 |
| OpenCompass LLM - Reasoning - English (CompassBench 2404) | 46.9 | Score (%) | 100 |
| OpenCompass Language - Content Summarization - Chinese (CompassBench 2404) | 35 | Score (%) | 100 |
| OpenCompass Language - Intention Recognition - English (CompassBench 2404) | 83.7 | Score (%) | 100 |
| OpenCompass Language - Sentiment Analysis - Chinese (CompassBench 2404) | 93 | Score (%) | 100 |
| OpenCompass Subjective - Average (CompassBench 2404) | 51.9 | Score (%) | 100 |
| OpenCompass Subjective - Knowledge (CompassBench 2404) | 55.8 | Score (%) | 100 |
Interactive version: theaggregate.ai/model?slug=sensechat-v5-0522 · How It Works · Data refreshed daily, snapshot 2026-11-08.