Artificials
Compare models
All makers

AI model maker

Baidu

5 models on Artificials, 1 with published test results and 3 with open weights you can download.

RSS feed
Best on the capability indexNot yetNone of its models is on the index yet
Best rankTop 9%ERNIE 5.1 on Arena math
Newest releaseERNIE 5.1May 10, 2026
Models51 tested, 3 with open weights

Where Baidu stands

Its best model’s rank among all models tested on each skill area’s main test, the same tests model pages use. A longer bar means a better rank.

  • OverallERNIE 5.1 on Arena text
    Top 11%
  • CodingERNIE 5.1 on Arena coding
    Top 13%
  • MathERNIE 5.1 on Arena math
    Top 9%
  • LanguageERNIE 5.1 on Arena creative writing
    Top 17%
  • ReasoningERNIE 5.1 on Arena hard prompts
    Top 12%

Every test

Its best result on each published test, and that result’s rank among every model tested. Scores from different tests are never combined.

TestBest modelScoreRank
Arena mathERNIE 5.11477#33 of 372
Arena textERNIE 5.11468#41 of 389
Arena hard promptsERNIE 5.11488#45 of 389
Arena codingERNIE 5.11512#47 of 384
Arena instruction followingERNIE 5.11453#50 of 389
Arena creative writingERNIE 5.11428#63 of 387

Every model

Newest first. The price is per 1M tokens, blended three input tokens to one output token: Baidu’s own listing, or else the middle price across hosts.

ModelReleasedContextPriceCapability index
ERNIE 5.1May 10, 2026119K tokens$1.31Not on the index
Ernie 5.0 Thinking PreviewNov 18, 2025128K tokens$1.47Not on the index
ERNIE 4.5 300B A47BJun 30, 2025123K tokens$0.485Not on the index
ERNIE 4.5 VL 424B A47BJun 30, 2025123K tokens$0.628Not on the index
Baidu Ernie 4.5 21B A3B ThinkingMar 16, 2025131.1K tokens$0.123Not on the index

Models, prices, context windows and release dates from models.dev (MIT). Test results from Arena (CC BY 4.0). A model counts here when Baidu sells it, several hosts list it or a test covers it. Each figure is the source’s own; nothing is combined into a new score.