Baidu model product
0 is Baidu's flagship foundation model featuring state-of-the-art performance across reasoning, mathematics, coding, and knowledge benchmarks.
Updated Aug 12, 2026. Default version: ERNIE 5.0
Technical details for the model's default version.
This profile uses the model's current scored version. Arena ratings and prices are shown separately.
Benchmark scores for ERNIE 5.0.
| SimpleQA | 75.0% | 05 | 46 | 91.1% | C | |
| MMLU-Pro | 87.0% | 08 | 129 | 94.5% | C | |
| Humanity's Last Exam | 39.0% | 36 | 93 | 62.0% | C | |
| GPQA | 85.0% | 54 | 234 | 77.3% | C | |
| AIME 2025 | 87.0% | 57 | 114 | 50.4% | C |
Preference and agent-evaluation results for the default version.
| vision | overall | 49 | 1247.7 | 3,154 | N/A | |
| text | overall | 50 | 1444.5 | 35,299 | N/A | |
| text | overall | 53 | 1442.5 | 9,778 | N/A | |
| vision style control | overall | 60 | 1217.8 | 3,154 | N/A | |
| text style control | overall | 61 | 1449.1 | 9,778 | N/A | |
| text factuality | overall | 66 | 1444.6 | 34,760 | N/A | |
| text style control | overall | 67 | 1446.4 | 35,299 | N/A | |
| text factuality | overall | 73 | 1441.4 | 9,537 | N/A | |
| text | overall | 76 | 1429.3 | 4,739 | N/A | |
| text factuality | overall | 76 | 1439.3 | 4,005 | N/A | |
| text style control | overall | 109 | 1418.3 | 4,739 | N/A |
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.
Official vendor API pricing appears first, followed by individual provider offers.
| ZenMux | baidu/ernie-5.0-thinking-preview | global | $0.84 | $3.37 | 128K |
Official prices use only the vendor's configured official Provider and positive standard USD PAYG rates. Third-party offers remain explicitly labeled.
Available versions of this model. The score column identifies the version used in the overall ranking.
| ERNIE 5.0 | 58.7 | N/A | N/A | N/A | No | Proprietary |
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 2026-08-11.
Open a comparison with the three ranked models immediately above and below this model.
Recommendations prioritize the same model type and family, then the closest LLMBoard score.
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.
Nearby ranked alternatives include GLM 4.7, Qwen3.5 122B A10B, GPT-5.2-Codex.