ERNIE 4.5 Turbo: benchmark results
Provider: Baidu. Released 2025-03-16. Access: API.
Aggregate Rating 1535 ± 42, rank #1900 of 10916 rated models, from 9 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| MediLongChat - In-Dialogue Reasoning | 31.74 | Token F1 (%) of short answers about a single consultation | 75 |
| LLM2014 Logic 2025-06 | 28.51 | Median Score | 25 |
| LLM2014 Logic 2025-05 | 33.28 | Median Score | 22.6 |
| LLM2014 Logic 2025-09 | 24.4 | Median Score | 20 |
| LLM2014 Logic 2025-10 | 24.4 | Median Score | 14.3 |
| LLM2014 Logic 2025-08 | 24.79 | Median Score | 13.6 |
| LLM2014 Logic 2025-11 | 20.56 | Median Score | 9.6 |
| ClawProBench | 33.68 | Final Score (imported) | 1.8 |
| MediLongChat - Cross-Dialogue Reasoning | 16.46 | Token F1 (%) of short answers linking facts across a patient | 0 |
Interactive version: theaggregate.ai/model?slug=ernie-4-5-turbo · How It Works · Data refreshed daily, snapshot 2026-11-08.