Model
Model explorer

ERNIE 5.0 (Preview)

CLOSED
Baidu · ERNIE family · released Nov 13, 2025

2.4T-parameter natively omni-modal flagship unveiled at Baidu World 2025; scored 22 on Artificial Analysis's Intelligence Index as a free preview.

ReasoningCodingVisionFunction callingTool useAgentic
1734.1
Elo · rank #86
Parameters
2400B
Active params
Undisclosed
Context
128K tokens
Architecture
Natively omni-modal Mixture-of-Experts, unified autoregressive next-token objective, <3% of experts active per token
License
Proprietary
Languages
—
API price (in/out)
No hosted API
Modalities
text · vision · audio · video
Benchmark results
Bar shows position within the tracked field; marker = field best
Arena EloHuman preference1451#8
best: Claude Fable 5 · 1505
GPQA DiamondReasoning78.0%#89
best: GPT-5.6 · 94.6%
Humanity's Last ExamReasoning13.0%#78
best: Claude Sonnet 5 · 57.4%
IFBenchReasoning41.0%#44
best: MiniMax M3 · 83.0%
MMMU-ProVision65.0%#36
best: Claude Opus 4.7 · 85.5%
Run it locally
Closed weights — available via API only. No local deployment.
Input / M tok
—
Output / M tok
—
ERNIE family
Elo progression across releases
ERNIE 3.0 TitanDec 20211000.0ERNIE Bot (ERNIE 3.5)Jun 2023436.1ERNIE 4.0Oct 20232345.9ERNIE X1Mar 20251000.0ERNIE 5.0 (Preview)Nov 20251734.1
Resources
DOCSernie.baidu.com/blog/posts/ernie5.0APIAvailable via Baidu API
API price — · each benchmark row carries its own source badge (see methodology)