ERNIE 5.0 — benchmark results
Baidu's proprietary multimodal ERNIE 5.0 flagship (November 2025). Provider: Baidu. Released 2025-11-13. Access: API.
Unified ELO 1609 ± 41, rank #462 of 1776 rated models, from 17 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| ZeroEval GPQA Diamond | 85 | GPQA Diamond Score | 77 |
| LLM2014 Logic 2026-01 | 41.43 | Median Score | 63.6 |
| OpenCompass Agent - Multi-Turn | 75.2 | Score (%) | 62 |
| LLM2014 Logic 2025-11 | 40.69 | Median Score | 57.7 |
| LLM2014 Logic 2026-02 | 34.53 | Median Score | 48.9 |
| LLM2014 Logic 2025-12 | 36.1 | Median Score | 44 |
| Position Bias (Lechmazur) | 45 | Order Flip % (lower is better) | 40 |
| LLM2014 Logic 2026-03 | 32.15 | Median Score | 36.6 |
| OpenCompass Code - Competition | 41.8 | Score (%) | 36 |
| OpenCompass Language - Dialogue | 94.1 | Score (%) | 36 |
| LLM2014 Logic 2026-04 | 28.37 | Median Score | 27.5 |
| Sycophancy (Lechmazur) | 8 | Sycophancy rate % (lower is better) | 27.4 |
Interactive version: theaggregate.ai/model?slug=ernie-5-0 · How the rankings work · Data refreshed daily, snapshot 2026-07-22.