ERNIE 4.5 — benchmark results

Provider: Baidu. Released 2025-03-16. Access: API.

Unified ELO 1391 ± 69, rank #1267 of 1776 rated models, from 11 benchmark results.

Strongest benchmark results

BenchmarkScoreMetricPercentile
AI for Education Visual Maths - Statistics and Probability28.57Accuracy (%)69.2
ZeroEval GPQA Diamond74GPQA Diamond Score51.5
AI for Education Visual Maths - Geometry33.85Accuracy (%)25.8
AI for Education Visual Maths - Number and Operations35.14Accuracy (%)22.5
AI for Education Visual Maths31.65Accuracy (%)18.3
AI for Education Visual Maths - Algebra30.77Accuracy (%)11.7
AI for Education Visual Maths - Measurement21.62Accuracy (%)8.3
LLM Stats (C-Eval)40.7Score (%)0
LLM Stats (CMMLU)39.8Score (%)0
LLM Stats (DROP)28.6Score (%)0
LLM Stats (MMLU-Redux)43.2Score (%)0

Interactive version: theaggregate.ai/model?slug=ernie-4-5 · How the rankings work · Data refreshed daily, snapshot 2026-07-22.