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 1612 ± 1, rank #230 of 1392 rated models, from 15 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| ZeroEval GPQA Diamond | 85 | GPQA Diamond Score | 75 |
| LLM Stats Score | 33.56 | LLM Stats Score (conservative rating) | 74.1 |
| LLM2014 Logic 2026-01 | 41.43 | Median Score | 63.6 |
| 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 |
| LLM2014 Logic 2026-04 | 28.37 | Median Score | 27.5 |
| AIIQ Composite IQ | 95 | Composite IQ (self-reported) | 21.5 |
| Persuasion (Lechmazur) | 0.77 | Average Persuasion Strength | 21.4 |
| Generalization V2 (Lechmazur) | 41.7 | Inverse-Rank Score | 20.7 |
Interactive version: theaggregate.ai/model?slug=ernie-5-0 · How It Works · Data refreshed daily, snapshot 2026-09-05.