Baidu model product
ERNIE 5.0
0 is Baidu's flagship foundation model featuring state-of-the-art performance across reasoning, mathematics, coding, and knowledge benchmarks.
Updated Aug 17, 2026. Default version: ERNIE 5.0
LLMBoard Score58.8ERNIE 5.0
Coverage60%5 benchmark families
Context windowN/ATokens
Official input priceN/AOfficial price unavailable
ERNIE 5.0 Capability Profile
This profile uses the model's current scored version. Arena ratings and prices are shown separately.
ERNIE 5.0 Benchmark Results
Benchmark scores for ERNIE 5.0.
Sort by
Benchmark | Score | Rank | Participants | Percentile | Evidence | Evaluated |
|---|
| BenchmarkSimpleQA | Score75.0% | Rank05 | Participants47 | Percentile91.3% | EvidenceC | Evaluated |
| BenchmarkMMLU-Pro | Score87.0% | Rank09 | Participants134 | Percentile94.0% | EvidenceC | Evaluated |
| BenchmarkHumanity's Last Exam | Score39.0% | Rank39 | Participants99 | Percentile61.2% | EvidenceC | Evaluated |
| BenchmarkAIME 2025 | Score87.0% | Rank57 | Participants115 | Percentile50.9% | EvidenceC | Evaluated |
| BenchmarkGPQA | Score85.0% | Rank58 | Participants239 | Percentile76.0% | EvidenceC | Evaluated |
ERNIE 5.0 Arena Results
Preference and agent-evaluation results for the default version.
Sort by
Arena | Category | Rank | Rating / score | Votes | Observations | Result date |
|---|
| Arenavision | Categoryoverall | Rank49 | Rating / score1247.7 | Votes3,154 | ObservationsN/A | Result date |
| Arenatext | Categoryoverall | Rank51 | Rating / score1444.5 | Votes35,304 | ObservationsN/A | Result date |
| Arenatext | Categoryoverall | Rank54 | Rating / score1442.5 | Votes9,780 | ObservationsN/A | Result date |
| Arenavision style control | Categoryoverall | Rank60 | Rating / score1217.8 | Votes3,154 | ObservationsN/A | Result date |
| Arenatext style control | Categoryoverall | Rank62 | Rating / score1449.0 | Votes9,780 | ObservationsN/A | Result date |
| Arenatext factuality | Categoryoverall | Rank67 | Rating / score1444.6 | Votes34,765 | ObservationsN/A | Result date |
| Arenatext style control | Categoryoverall | Rank68 | Rating / score1446.4 | Votes35,304 | ObservationsN/A | Result date |
| Arenatext factuality | Categoryoverall | Rank74 | Rating / score1441.3 | Votes9,539 | ObservationsN/A | Result date |
| Arenatext | Categoryoverall | Rank77 | Rating / score1429.2 | Votes4,736 | ObservationsN/A | Result date |
| Arenatext factuality | Categoryoverall | Rank77 | Rating / score1439.1 | Votes4,002 | ObservationsN/A | Result date |
| Arenatext style control | Categoryoverall | Rank110 | Rating / score1418.1 | Votes4,736 | ObservationsN/A | Result date |
ERNIE 5.0 Pricing
Official vendor API pricing appears first, followed by individual provider offers.
- Official API
- N/A
- Official provider
- N/A
- Lowest third-party
- From $0.84 input, $3.37 output per 1M via ZenMux
- Tracked offerings
- 1
Sort by
Provider | Provider model ID | Region | Input / 1M | Output / 1M | Context | Updated |
|---|
| ProviderZenMux | Provider model IDbaidu/ernie-5.0-thinking-preview | Regionglobal | Input / 1M$0.84 | Output / 1M$3.37 | Context128K | Updated |
Official prices use only the vendor's configured official Provider and positive standard USD PAYG rates. Third-party offers remain explicitly labeled.
ERNIE 5.0 Runtime Performance
Provider-specific output speed and catalog latency for ERNIE 5.0. Runtime does not affect the capability score.
No runtime data
Browse runtime rankingsNo provider-specific speed or latency record is linked to the default version yet.
Output Speed is generated output tokens received per second. Catalog latency is reported separately from observed provider TTFT.
ERNIE 5.0 Specifications
Technical details for the model's default version.
- Version
- ERNIE 5.0
- Released
- Jan 22, 2026
- Knowledge cutoff
- Unknown
- Parameters
- N/A
- Context window
- N/A
- Max output
- N/A
- Inputs
- image, text
- Outputs
- text
- Open weights
- No
- License
- Proprietary
ERNIE 5.0 Versions
Available versions of this model. The score column identifies the version used in the overall ranking.
Sort by
Version | Released | LLMBoard | Parameters | Context | Max output | Open weights | License |
|---|
| VersionERNIE 5.0 | Released | LLMBoard58.8 | ParametersN/A | ContextN/A | Max outputN/A | Open weightsNo | LicenseProprietary |
ERNIE 5.0 vs nearby models
Open a comparison with the three ranked models immediately above and below this model.
Models similar to ERNIE 5.0
Recommendations prioritize the same model type and family, then the closest LLMBoard score.
BA
ERNIE 4.5
Baidu
AC
Qwen3.5 122B A10B
Alibaba Cloud / Qwen Team
ME
Muse Glimmer 30B
Meta
MI
MiniMax M2.7
MiniMax
OP
GPT-5.2-Codex
OpenAI
ZA
GLM 4.7
Zhipu AI
What is ERNIE 5.0?
Key information about ERNIE 5.0 and its available data.
0 is Baidu's flagship foundation model featuring state-of-the-art performance across reasoning, mathematics, coding, and knowledge benchmarks. 5 with enhanced multilingual capabilities, improved instruction following, and stronger agentic task performance.
Data as of 2026-08-17.
FAQ
Common questions about ERNIE 5.0.
When was ERNIE 5.0 released?
ERNIE 5.0's default version was released on Jan 22, 2026.
How much does ERNIE 5.0 cost?
No official standard PAYG price is currently available for ERNIE 5.0. The lowest tracked third-party offer starts at $0.84 input and $3.37 output via ZenMux.
Who created ERNIE 5.0?
ERNIE 5.0 was created by Baidu.
What is the context window for ERNIE 5.0?
A context window is not available for the default version.
Is ERNIE 5.0 open weight?
No. The default version is not marked as having publicly available weights.
How many API providers offer ERNIE 5.0?
1 provider offerings are linked to the default version.
What models should I compare ERNIE 5.0 with?
Nearby ranked alternatives include GPT-5.2-Codex, MiniMax M2.7, Qwen3.5 122B A10B.