Baidu model product
0 is Baidu’s foundation model for reasoning, mathematics, coding, and knowledge tasks.
Updated Sep 8, 2026. Default version: ERNIE 5.0
This profile uses the model's current scored version. Arena ratings and prices are shown separately.
Benchmark scores for ERNIE 5.0.
Benchmark | Score | Rank | Participants | Percentile | Evidence | Evaluated |
|---|
| BenchmarkSimpleQA | Score75.00% | Rank05 | Participants47 | Percentile91.30% | EvidenceC | Evaluated |
| BenchmarkMMLU-Pro | Score87.00% | Rank09 | Participants138 | Percentile94.16% | EvidenceC | Evaluated |
| BenchmarkHumanity's Last Exam | Score39.00% | Rank41 | Participants103 | Percentile60.78% | EvidenceC | Evaluated |
| BenchmarkLM Arena Vision | Score1,248.46 rating | Rank41 | Participants107 | Percentile62.26% | EvidenceA | Evaluated |
| BenchmarkLM Arena Text | Score1,444.40 rating | Rank44 | Participants210 | Percentile79.43% | EvidenceA | Evaluated |
| BenchmarkLM Arena Vision Style Control | Score1,218.85 rating | Rank52 | Participants107 | Percentile51.89% | EvidenceA | Evaluated |
| BenchmarkLM Arena Text Style Control | Score1,448.86 rating | Rank54 | Participants210 | Percentile74.64% | EvidenceA | Evaluated |
| BenchmarkLM Arena Text Factuality | Score1,444.49 rating | Rank55 | Participants121 | Percentile55.00% | EvidenceA | Evaluated |
| BenchmarkAIME 2025 | Score87.00% | Rank59 | Participants119 | Percentile50.85% | EvidenceC | Evaluated |
| BenchmarkGPQA | Score85.00% | Rank62 | Participants247 | Percentile75.20% | EvidenceC | Evaluated |
Preference and agent-evaluation results for the default version.
Arena | Category | Rank | Rating / score | Votes | Observations | Result date |
|---|
| Arenavision | Categorycreative writing | Rank02 | Rating / score1,336.08 | Votes176 | ObservationsN/A | Result date |
| Arenavision style control | Categorycreative writing | Rank02 | Rating / score1,304.97 | Votes176 | ObservationsN/A | Result date |
| Arenatext | Categoryspanish | Rank11 | Rating / score1,475.79 | Votes235 | ObservationsN/A | Result date |
| Arenatext | Categorypolish | Rank12 | Rating / score1,483.88 | Votes344 | ObservationsN/A | Result date |
| Arenatext style control | Categorypolish | Rank14 | Rating / score1,486.57 | Votes344 | ObservationsN/A | Result date |
| Arenatext style control | Categoryspanish | Rank15 | Rating / score1,473.62 | Votes235 | ObservationsN/A | Result date |
| Arenatext | Categoryindustry medicine and healthcare | Rank18 | Rating / score1,472.42 | Votes672 | ObservationsN/A | Result date |
| Arenatext style control | Categoryindustry medicine and healthcare | Rank20 | Rating / score1,489.81 | Votes672 | ObservationsN/A | Result date |
| Arenatext | Categorygerman | Rank24 | Rating / score1,460.23 | Votes220 | ObservationsN/A | Result date |
| Arenatext factuality | Categoryspanish | Rank24 | Rating / score1,450.04 | Votes798 | ObservationsN/A | Result date |
| Arenatext factuality | Categorypolish | Rank25 | Rating / score1,427.65 | Votes579 | ObservationsN/A | Result date |
| Arenatext | Categorychinese | Rank26 | Rating / score1,509.33 | Votes381 | ObservationsN/A | Result date |
| Arenatext style control | Categoryfrench | Rank27 | Rating / score1,487.36 | Votes250 | ObservationsN/A | Result date |
| Arenatext factuality | Categorychinese | Rank28 | Rating / score1,502.62 | Votes1,438 | ObservationsN/A | Result date |
| Arenatext | Categoryfrench | Rank29 | Rating / score1,471.83 | Votes250 | ObservationsN/A | Result date |
| Arenatext factuality | Categoryindustry life and physical and social science | Rank31 | Rating / score1,482.42 | Votes1,064 | ObservationsN/A | Result date |
| Arenatext | Categoryindustry legal and government | Rank33 | Rating / score1,461.37 | Votes323 | ObservationsN/A | Result date |
| Arenatext factuality | Categoryindustry medicine and healthcare | Rank34 | Rating / score1,481.02 | Votes1,517 | ObservationsN/A | Result date |
| Arenatext | Categoryindustry life and physical and social science | Rank35 | Rating / score1,466.07 | Votes1,597 | ObservationsN/A | Result date |
| Arenatext factuality | Categorymath | Rank35 | Rating / score1,447.65 | Votes1,376 | ObservationsN/A | Result date |
| Arenatext factuality | Categorycreative writing | Rank36 | Rating / score1,438.31 | Votes960 | ObservationsN/A | Result date |
| Arenatext style control | Categorygerman | Rank36 | Rating / score1,460.91 | Votes220 | ObservationsN/A | Result date |
| Arenatext | Categorykorean | Rank38 | Rating / score1,404.42 | Votes632 | ObservationsN/A | Result date |
| Arenatext | Categorynon english | Rank39 | Rating / score1,435.89 | Votes20,323 | ObservationsN/A | Result date |
| Arenatext | Categorycreative writing | Rank41 | Rating / score1,425.65 | Votes5,463 | ObservationsN/A | Result date |
| Arenatext | Categoryexclude ties | Rank41 | Rating / score1,443.03 | Votes24,850 | ObservationsN/A | Result date |
| Arenatext factuality | Categoryrussian | Rank41 | Rating / score1,456.68 | Votes2,763 | ObservationsN/A | Result date |
| Arenatext style control | Categoryindustry life and physical and social science | Rank41 | Rating / score1,478.29 | Votes1,597 | ObservationsN/A | Result date |
| Arenavision | Categoryoverall | Rank41 | Rating / score1,248.46 | Votes3,233 | ObservationsN/A | Result date |
| Arenatext | Categoryrussian | Rank42 | Rating / score1,445.33 | Votes4,270 | ObservationsN/A | Result date |
Official vendor API pricing appears first, followed by individual provider offers.
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.
Provider-specific output speed and catalog latency for ERNIE 5.0. Runtime does not affect the capability score.
No 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.
Technical details for the model's default version.
Available versions of this model. The score column identifies the version used in the overall ranking.
Version | Released | LLMBoard | Parameters | Context | Max output | Open weights | License |
|---|
| VersionERNIE 5.0 | Released | LLMBoard59.74 | ParametersN/A | ContextN/A | Max outputN/A | Open weightsNo | LicenseProprietary |
Recommendations prioritize the same model type and family, then the closest LLMBoard score.
Key information about ERNIE 5.0 and its available data.
0 is a Baidu foundation model with multilingual capabilities, instruction following, and agentic task performance. 5 across these areas.
Data as of 2026-09-08.
Common questions about ERNIE 5.0.
ERNIE 5.0's default version was released on Jan 22, 2026.
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.
ERNIE 5.0 was created by Baidu.
A context window is not available for the default version.
No. The default version is not marked as having publicly available weights.
1 provider offerings are linked to the default version.