Baichuan4: benchmark results
Provider: Baichuan.
Aggregate Rating 1531 ± 21, rank #1944 of 10916 rated models, from 262 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| OpenCompass Agent - T-Eval - English (CompassBench 2405) | 87.8 | Score (%) | 97.4 |
| OpenCompass Agent - CIBench - Chinese (CompassBench 2405) | 71.8 | Score (%) | 94.7 |
| OpenCompass Agent - CIBench - English (CompassBench 2405) | 75.1 | Score (%) | 94.7 |
| OpenCompass LLM - Agent (CompassBench 2405) | 79.1 | Score (%) | 94.7 |
| OpenCompass LLM - Agent - Chinese (CompassBench 2405) | 76.7 | Score (%) | 94.7 |
| OpenCompass LLM - Agent - English (CompassBench 2405) | 81.4 | Score (%) | 94.7 |
| OpenCompass Agent - T-Eval - English (CompassBench 2407) | 87.7 | Score (%) | 94.1 |
| OpenCompass Math - Primary School - English (CompassBench 2405) | 86.7 | Score (%) | 92.1 |
| OpenCompass Subjective - Reasoning - Chinese (CompassBench 2405) | 45.3 | Score (%) | 92.1 |
| OpenCompass Language - Intention Recognition - Chinese (CompassBench 2405) | 72.7 | Score (%) | 89.5 |
| OpenCompass Subjective - Code - English (CompassBench 2405) | 43.4 | Score (%) | 89.5 |
| OpenCompass Subjective - Creation - English (CompassBench 2405) | 46.6 | Score (%) | 89.5 |
Interactive version: theaggregate.ai/model?slug=baichuan4 · How It Works · Data refreshed daily, snapshot 2026-11-08.