BaiduNovember 5, 2026

ERNIE 5.5 Flash Base

Baidu ERNIE 5.5 Flash Base

Baidu's open-weight 280B/14B hybrid-attention MoE base model released Nov 5, 2026: pre-trained on 33.5T tokens with 1M inference context, FP8/BF16 checkpoints; MMLU 93.3, HumanEval+ 82.3, RepoQA 91.7.

Text inputText outputOpen weights

At a glance

Context window
1M tokens
Max output
—
Text input / output · per 1M tokens
— / —
Knowledge cutoff
—

Benchmark snapshot

Best result in each categories

  • AcademicMMLU

    93.3

    Normal (No Tools) · #2 of 114

  • CodingMBPP

    81.5

    Normal (No Tools) · #17 of 67

  • Long ContextLongBench v2

    48.7

    Normal (No Tools) · #19 of 22

  • ReasoningBBH

    77.1

    Normal (No Tools) · limited comparability · #12 of 20

  • Safety & AlignmentSimpleQA

    34.1

    Normal (No Tools) · #23 of 46

View benchmark details (9)

Benchmark details

9 results · Best published score per benchmark, grouped by category

Benchmark · settingScoreRank
Academic
GPQA

Normal (No Tools) · Scientific Reasoning

60.26 / 15
MMLU

Normal (No Tools) · Knowledge Exams

93.32 / 114
MMLU-Pro

Normal (No Tools) · Knowledge Exams

78.469 / 153
Coding
HumanEval

Normal (No Tools) · Code Generation & Editing

82.338 / 100
LiveCodeBench

Normal (No Tools) · Algorithmic Coding

40.194 / 113
MBPP

Normal (No Tools) · Code Generation & Editing

81.517 / 67
Long Context
LongBench v2

Normal (No Tools) · Long Reasoning

48.719 / 22
Reasoning
BBH

Normal (No Tools) · limited comparability · General Reasoning

77.112 / 20
Safety & Alignment
SimpleQA

Normal (No Tools) · Honesty & Factuality

34.123 / 46

Rank is this model's position among every model with a published result on that leaderboard; the bar shows how far up the field that is. Orange marks first place on leaderboards with at least 5 models. Unranked leaderboards publish a composite or direction-less score.

Back to benchmark snapshot ↑

Specifications

Provider
Baidu
Model type
Foundation model
Released
November 5, 2026
Total parameters
280B
Active parameters
14B
Architecture
Mixture of experts
Context window
1M tokens
Input
Text
Output
Text
Licence
Open weights (license unspecified)
Commercial use
Not documented

Capabilities

MultilingualCodingLong context

Model analysis

ERNIE-5.5-Flash-Base is Baidu's open-weight sparse Mixture-of-Experts (MoE) base model released on November 5, 2026, featuring 280B total parameters and 14B activated parameters per token, pre-trained from scratch on 33.5T tokens.

Architecture and Technical Highlights

  • 280B-A14B Hybrid-Attention MoE: 43 layers (1 dense FFN + 42 Multi-Router Latent MoE) combining 37 Heavily Compressed Attention (HCA, 1 cache entry per 128 tokens, 512-dim heads) and 6 Multi-head Latent Attention layers with sparse attention (MLA + DSA, 256-dim heads); 512 routed experts (top-10) plus 1 shared expert per MoE layer in a 2048-d latent space, excluding 0.36B ECHO parameters.
  • Context Window and Tokenizer: Pre-trained up to 128K (131,072 tokens) and supporting 1M (1,048,576 tokens) for fine-tuning and inference, with a 201,216-entry BPE vocabulary using right-to-left 3-digit number grouping.
  • Key Innovations: Low-Rank Gated Attention and Virtual Head Attention (VHA, arXiv:2610.17959), Multi-Router Latent MoE (arXiv:2610.40577), ECHO backbone-reused multi-token prediction (arXiv:2610.24766), Manifold-constrained Hyper-Connections (mHC, expansion rate 4), and MultiMax output head, trained with distributed Muon and FlashMask-4.

Pre-training Benchmark Results

Under Baidu's unified evaluation pipeline across 30 benchmarks, ERNIE-5.5-Flash-Base leads comparably sized open base models: MMLU 93.3, MMLU-Redux 94.1, MMLU-Pro 78.4, CMMLU 90.0, GPQA 60.2, MGSM 87.0, MathBench-CN 80.8, HumanEval+ 82.3, MBPP+ 81.5, LiveCodeBench 40.1, RepoQA 91.7, and LongBench-v2 48.7.

Open Weights and Serving

FP8 (baidu/ERNIE-5.5-Flash-Base) and BF16 (baidu/ERNIE-5.5-Flash-Base-BF16) safetensors checkpoints are available on Hugging Face and ModelScope with SGLang and vLLM serving support under the ERNIE 5.5 Flash Base Model License Agreement v1.0.

Sources

Last reviewed 2026-11-16

Questions

What are the parameter count and architecture of ERNIE-5.5-Flash-Base?
ERNIE-5.5-Flash-Base has 280B total parameters and 14B activated parameters per token (excluding 0.36B ECHO parameters) across 43 layers, using 37 HCA layers, 6 MLA-DSA layers, and Multi-Router Latent MoE.
What context length does ERNIE-5.5-Flash-Base support?
It was pre-trained with a context length of up to 128K (131,072 tokens) and supports 1M (1,048,576 tokens) for fine-tuning and inference.
Where are ERNIE-5.5-Flash-Base weights hosted and what license applies?
FP8 and BF16 checkpoints are hosted on Hugging Face and ModelScope under the ERNIE 5.5 Flash Base Model License Agreement v1.0, with SGLang and vLLM serving support.

ERNIE 5.5 Flash Base vs competitors

Comparable results only · record is ERNIE 5.5 Flash Base's wins–losses

ERNIE 5.5 Flash Base benchmark scores against competitors
BenchmarkERNIE 5.5 Flash BaseThis modelvs Gemma 3 - 27B (IT)Record 6–2vs Llama3.1-405B InstructRecord 4–3vs Hunyuan-A13B-InstructRecord 3–3vs Mistral-Small-3.1-24B-Instruct-2503Record 5–1
MMLU-Pro78.467.573.467.266.8
MMLU93.378.688.688.280.6
MBPP81.574.488.683.974.7
LiveCodeBench40.129.730.263.9—
HumanEval82.387.889.0—88.4
SimpleQA34.110.017.1—10.4
BBH77.187.689.289.1—
GPQA60.236.8—49.144.4

Lineage

Predecessors and successors · oldest to newest

  1. ERNIE 5.5 Flash BaseThis model · Nov 5, 2026vs ERNIE-4.5-300B-A47B-Base

Price & benchmark trends

Across curated predecessors and successors, ordered by release date. Points use listed rates and published results, not a history of price changes within one model. Related branches may appear; adjacent points do not imply direct succession. Undated models appear last.

API price across generations

Text inputText outputUSD / 1M tokens

At least two recorded values are needed for a trend. Available values appear below.

Input and output share one linear USD axis · uncached text rates · lower is cheaper. Retired models may retain their last recorded price. Rate tiers and context limits can differ; inspect each model's pricing conditions.

Orange marks this model. Hover, tap or focus the chart to see exact values. Missing values leave gaps. Horizontal spacing shows release order, not elapsed time.

Listed prices and selected benchmark scores across model generations
Model · releasedInput / 1MOutput / 1MPrice effective
1ERNIE-4.5-300B-A47B-BaseJun 30, 2025——Not recorded
2ERNIE 5.5 Flash BaseNov 5, 2026 · This model——Not recorded
3ERNIE 5.5 Flash PreviewNov 11, 2026——Not recorded

Community discussion

Share the API, setup, and tradeoffs you actually tested. Rate the model once; comment as often as you like.

Used this model? Sign in with Google to rate it and share what worked, what did not, and which API or setup you tested.

No community comments yet.