Skip to content
VECTOR WIREAI INTELLIGENCE
⌘K
UTC
Models741Deals30d261Policy30d65, 14 pendingSources1,013

ERNIE 5.0 Thinking Preview

BaiduReleased Nov 13, 2025Current

Score basis

ERNIE 5.0 Thinking Preview is behind the leaders in multimodal tasks, reasoning, factuality, agentic tasks, and instruction following. Too few results yet to rate coding, safety, long context, math, or multilingual tasks.

Capability profile

Bars show the model's median result as a share of the leading model's, per capability. Select a row to see its results.

Limited5 capabilities
  1. Multimodal−34.5%1 of 6
  2. Reasoning−37.1%3 of 6
  3. Factuality−39.3%2 of 4
  4. Agentic−40.6%1 of 7
  5. Instruction Following−44.5%1 of 3
Not rated5 capabilities

Too few results yet to rate Coding, Safety, Long Context, Math or Multilingual.

Price

$0.89input$3.58outputper million tokens

From Baidu's own price page · All prices

Costs more than 67% of 331 priced models · 3:1 input-to-output blend, log scale

Evidence

21results on19benchmarks

  • 16 aggregator
  • 5 vendor-reported

From 2 sources · latest Oct 8, 2026 · How verification works

ERNIE 5.0 Thinking Preview benchmark results

21 results on 19 benchmarks, grouped by capability. Each bar is the result as a share of the capability leader's; every result links to its source.

Multimodal

LimitedFull multimodal ranking

34.5% behind the leader1 of 6 ranked benchmarks measured

Reasoning

LimitedFull reasoning ranking

37.1% behind the leader3 of 6 ranked benchmarks measured

Show 2 more reasoning resultsHide 2 reasoning results

Factuality

LimitedFull factuality ranking

39.3% behind the leader2 of 4 ranked benchmarks measured

Agentic

LimitedFull agentic ranking

40.6% behind the leader1 of 7 ranked benchmarks measured

Instruction Following

LimitedFull instruction following ranking

44.5% behind the leader1 of 3 ranked benchmarks measured

Coding

Not enough dataFull coding ranking

0 of 10 ranked benchmarks measured

Long Context

Not enough dataFull long context ranking

0 of 3 ranked benchmarks measured

More results

Benchmarks outside the capability baskets. They are not ranked against a leader.

Show 2 more resultsHide 2 results

ERNIE 5.0 Thinking Preview: common questions

Who makes ERNIE 5.0 Thinking Preview?

ERNIE 5.0 Thinking Preview is made by Baidu.

When was ERNIE 5.0 Thinking Preview released?

ERNIE 5.0 Thinking Preview was released on Nov 13, 2025, according to Artificial Analysis.

What is ERNIE 5.0 Thinking Preview good at?

ERNIE 5.0 Thinking Preview is behind the leaders in multimodal tasks, reasoning, factuality, agentic tasks, and instruction following. Too few results yet to rate coding, safety, long context, math, or multilingual tasks.

How much does ERNIE 5.0 Thinking Preview cost?

ERNIE 5.0 Thinking Preview costs $0.89 per million input tokens and $3.58 per million output tokens, according to Baidu's own price page. At a mix of three input tokens to one output token, it costs more than 67% of the 331 priced models we track.

How many benchmarks has ERNIE 5.0 Thinking Preview been tested on?

We track 21 results for ERNIE 5.0 Thinking Preview on 19 benchmarks from 2 sources. The latest was recorded on Oct 8, 2026.

About this record

Where ERNIE 5.0 Thinking Preview's numbers come from, and every name it appears under.

Tracked since
May 2, 2026
Newest source mention
May 2, 2026

Where the results come from

Verification: 21 scores · 0 independently verified · 16 aggregator-attributed · 5 vendor-reported. How these tiers are assigned

From 2 sources on 2 sites. Artificial Analysis supplies 16 of them. Bars are coloured by trust tier.

  • artificialanalysis.ai16
  • api.llm-stats.com5

Also known as

ernie-5.0