Skip to content

Baidu · Chat

ERNIE 4.5 21B A3B

Baidu 🇨🇳ChatOpen weights. One of its sources says the weights are publicly available.
llminfo IQ
≈ 107
Market median price
$0.1225 blended / 1M
Max context
131K
Listings
8

Evidence and sources

🤗 baidu/ERNIE-4.5-21B-A3B-Thinkingllminfo IQ ≈ 107, ranked among chat models. From 37 benchmarks. Little data behind it, so treat it as a rough estimate.How llminfo IQ is computedPoor value (46.6). Costs more per task than its benchmark results predict. From 1 benchmark with measured task costs. Little data behind it, so treat it as a rough estimate.How Value for money worksReleased 8 Sep 2025Maker HQ: CN (according to Baidu's own website)
Sources: Helicone Costs data, Models.dev data, Hugging FacePrimary data from Helicone Costs from Models.dev: name, weights availability from Hugging Face: release date

Advantages and trade-offs

Compared with 10 chat models, picked mainly by popularity and IQ

Advantages

Open weights available

The weights are public. 3 of the 7 peers that say either way have open weights.

Trade-offs

We only make a claim when there's enough data on models of the same type. Updated 22 Nov, 06:07 UTC.Prices come from the model's maker where they sell it, otherwise their official partner, otherwise the market median. This comparison uses 6 maker's prices; 3 market median prices.

Input & output

as stated by the model's providers
Text
Text

Capabilities

Supported operations and provider-stated features

ReasoningFunction calling

Listings

 302aibaidu/ernie-4.5-21B-a3bSource: 302.ai data120K$0.072$0.286
 302aibaidu/ernie-4.5-21b-a3b-thinking · thinkingSource: 302.ai data131K$0.072$0.286
 Flowdotbaidu/ernie-4.5-21b-a3bSource: FlowDot data120K$0.07$0.28
 Flowdotbaidu/ernie-4.5-21b-a3b-thinking · thinkingSource: FlowDot data131K$0.07$0.28
 OpenRouterbaidu/ernie-4.5-21b-a3bSource: Helicone Costs dataNot published by the provider$0.07$0.28
 OpenRouterbaidu/ernie-4.5-21b-a3b-thinking · thinkingSource: Helicone Costs dataNot published by the provider$0.07$0.28
 Novita AInovita/baidu/ernie-4.5-21B-a3bSources: LiteLLM data, Models.dev data120K$0.07$0.28
 Novita AInovita/baidu/ernie-4.5-21B-a3b-thinking · thinkingSource: LiteLLM data131K$0.07$0.28

These providers advertise this model. Researchers have found some resellers serving a different, cheaper model, so see how to check whether a provider meets your needs.

Benchmarks

Named effort levels run from lowest to highest. Select a result to see its source details.

Reasoning

Coding

Human preference

Other

Nejumi 428 related benchmarks · 28 results

Data credits: Nejumi Leaderboard 4, Weights & Biases Japan; public publisher-selected numeric evaluation results · SnakeBench (Greg Kamradt / ARC Prize Foundation), MIT (licence)

Around the web

Also known as: baidu/ernie-4.5-21b-a3b, baidu/ernie-4.5-21b-a3b-thinking, ernie-4.5-21b-a3b-thinking, novita/baidu/ernie-4.5-21b-a3b, novita/baidu/ernie-4.5-21b-a3b-thinking

Like this one. Tap or hover any dotted value, label or icon to see where it comes from and how it is measured. open details when tapped or hovered. How this data works