Baidu model product
5 Flash is Baidu’s text-only mixture-of-experts model with 280 billion total parameters, 14 billion active parameters, and a 1,048,576-token context window.
Updated Nov 22, 2026. Default version: ERNIE 5.5 Flash Preview
This profile uses the model's current scored version. Arena ratings and prices are shown separately.
Benchmark scores for ERNIE 5.5 Flash Preview.
Benchmark | Score | Rank | Participants | Percentile | Evidence | Evaluated |
|---|
| BenchmarkAutomationBench | Score61.90% | Rank01 | Participants33 | Percentile100.00% | EvidenceC | Evaluated |
| BenchmarkSpreadsheetBench 2 | Score36.40% | Rank01 | Participants4 | Percentile100.00% | EvidenceC | Evaluated |
| BenchmarkDRACO | Score84.90% | Rank02 | Participants5 | Percentile75.00% | EvidenceC | Evaluated |
| BenchmarkNL2Repo | Score64.80% | Rank02 | Participants27 | Percentile96.15% | EvidenceC | Evaluated |
| BenchmarkAPEX-Agents | Score64.20% | Rank03 | Participants16 | Percentile86.67% | EvidenceC | Evaluated |
| BenchmarkMCP Atlas | Score84.60% | Rank04 | Participants44 | Percentile93.02% | EvidenceC | Evaluated |
| BenchmarkOfficeQA Pro | Score67.90% | Rank04 | Participants15 | Percentile78.57% | EvidenceC | Evaluated |
| BenchmarkHumanity's Last Exam (no tools, text-only) | Score46.40% | Rank05 | Participants15 | Percentile71.43% | EvidenceC | Evaluated |
| BenchmarkBrowseComp | Score87.40% | Rank11 | Participants78 | Percentile87.01% | EvidenceC | Evaluated |
| BenchmarkTerminal-Bench 4.0 | Score46.50% | Rank15 | Participants41 | Percentile65.00% | EvidenceC | Evaluated |
| BenchmarkTerminal-Bench-Science 0.1 | Score21.00% | Rank16 | Participants17 | Percentile6.25% | EvidenceC | Evaluated |
| BenchmarkDeepSWE 1.1 | Score71.20% | Rank20 | Participants59 | Percentile67.24% | EvidenceC | Evaluated |
| BenchmarkAgents' Last Exam | Score29.00% | Rank25 | Participants33 | Percentile25.00% | EvidenceC | Evaluated |
Preference and agent-evaluation results for the default version.
The default version does not have a matching Arena result yet.
Official vendor API pricing appears first, followed by individual provider offers.
The default version has no current input or output token prices.
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 5.5 Flash Preview. 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 5.5 Flash Preview | Released | LLMBoard82.25 | Parameters280B | Context1M | Max output1M | Open weightsNo | LicenseProprietary |
Recommendations prioritize the same model type and family, then the closest LLMBoard score.
Key information about ERNIE 5.5 Flash and its available data.
5 Flash Base. It is an intermediate post-training checkpoint.
Data as of 2026-11-21.
Common questions about ERNIE 5.5 Flash.
ERNIE 5.5 Flash's default version was released on Nov 11, 2026.
No official standard PAYG price is currently available for ERNIE 5.5 Flash.
ERNIE 5.5 Flash was created by Baidu.
The default version has a 1M token context window.
No. The default version is not marked as having publicly available weights.
No provider offering is currently linked to the default version.