Baichuan2-13B-Chat: benchmark results
Provider: Baichuan. Released 2023-09-06. Access: Open.
Unified ELO 1430 ± 17, rank #1659 of 2656 rated models, from 115 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| OpenCompass Reasoning - Inductive - English (CompassBench 2404) | 32.3 | Score (%) | 73.3 |
| SuperCLUE-Agent (October 2023) - Tool Use | 61.11 | Score | 72.2 |
| SuperCLUE General (September 2023) - Open-Ended Questions (OPEN) | 52.45 | Score | 68.4 |
| OpenCompass Language - Translation (CompassBench 2404) | 15.4 | Score (%) | 68.3 |
| OpenCompass LLM - Reasoning - English (CompassBench 2404) | 29.4 | Score (%) | 66.7 |
| SuperCLUE-Agent (October 2023) - Overall | 52.44 | Score | 66.7 |
| SuperCLUE General (September 2023) - Overall | 58.03 | Score | 63.2 |
| SuperCLUE-Agent (October 2023) - Long & Short-term Memory | 52.74 | Score | 61.1 |
| OpenCompass Reasoning - Abductive - English (CompassBench 2404) | 66 | Score (%) | 58.6 |
| OpenCompass Subjective - Knowledge (CompassBench 2404) | 28.5 | Score (%) | 58 |
| OpenCompass Reasoning - Deductive - Chinese (CompassBench 2404) | 25.1 | Score (%) | 56.7 |
| SuperCLUE-Agent (October 2023) - Task Planning | 40.48 | Score | 55.6 |
Interactive version: theaggregate.ai/model?slug=baichuan2-13b-chat · How It Works · Data refreshed daily, snapshot 2026-09-19.