/blog/posts/ Recent content in Posts on ERNIE Blog /blog/images/papermod-cover.png /blog/images/papermod-cover.png Hugo -- 0.148.0 en Copyright © 2025 Baidu, Inc. All Rights Reserved. Sat, 09 May 2026 00:00:00 +0000 /blog/posts/ernie-5.1-0508-release/ Sat, 09 May 2026 00:00:00 +0000 /blog/posts/ernie-5.1-0508-release/ ERNIE 5.1 is officially released, achieving leading performance at only 6% of the pre-training cost of comparable models. Powered by disaggregated fully-asynchronous reinforcement learning and scaled agentic post-training, ERNIE 5.1 delivers comprehensive upgrades across Agent, reasoning, and creative capabilities, ranking 1st in China on the Arena Search Arena. /blog/posts/ernie-5.1-preview-0430-release-on-lmarena/ Thu, 30 Apr 2026 00:00:00 +0000 /blog/posts/ernie-5.1-preview-0430-release-on-lmarena/ On April 30, LMArena released its latest rankings. ERNIE-5.1-Preview ranked No. 1 among Chinese models and No. 13 globally on the LMArena Text Arena, placing in the global top 10 across multiple category leaderboards. /blog/posts/ernie-image/ Wed, 15 Apr 2026 00:00:00 +0000 /blog/posts/ernie-image/ ERNIE-Image is a text-to-image generation model built on a single-stream Diffusion Transformer (DiT) with 8B DiT parameters, achieving leading performance among open-weights models. /blog/posts/ernie5.0/ Fri, 06 Feb 2026 00:00:00 +0000 /blog/posts/ernie5.0/ We introduce ERNIE 5.0: a 2.4 trillion-parameter Unified Multimodal Model trained from scratch. Integrating text, image, video, and audio into a single autoregressive framework, it overcomes the limitations of late-fusion architectures to achieve seamless cross-modal understanding and generation. /blog/posts/paddleocr-vl-1.5/ Thu, 29 Jan 2026 00:00:00 +0000 /blog/posts/paddleocr-vl-1.5/ 🚀 We release PaddleOCR-VL-1.5, an upgraded model achieving a new state-of-the-art (SOTA)accuracy of 94.5% on OmniDocBench v1.5. /blog/posts/ernie-5.0-0110-release-on-lmarena/ Thu, 15 Jan 2026 00:00:00 +0000 /blog/posts/ernie-5.0-0110-release-on-lmarena/ On January 15, LMArena released its latest rankings. ERNIE-5.0-0110 achieved a score of 1,460, ranking No. 1 among Chinese models and No. 8 globally on the LMArena Text Arena. /blog/posts/ernie-5.0-preview-1220-release-on-lmarena/ Thu, 08 Jan 2026 00:00:00 +0000 /blog/posts/ernie-5.0-preview-1220-release-on-lmarena/ On January 8, LMArena released its latest rankings. ERNIE-5.0-Preview-1220 achieved a score of 1226, ranking No. 1 in China and No. 8 globally on the LMArena Vision Arena. /blog/posts/ernie-5.0-preview-1203-release-on-lmarena/ Tue, 23 Dec 2025 00:00:00 +0000 /blog/posts/ernie-5.0-preview-1203-release-on-lmarena/ Just now, LMArena released its latest rankings. Baidu’s ERNIE-5.0-Preview-1203 scored an impressive 1,451 points. /blog/posts/ernie-5.0-preview-1103-release-on-lmarena/ Tue, 09 Dec 2025 00:00:00 +0000 /blog/posts/ernie-5.0-preview-1103-release-on-lmarena/ We’ve just refreshed our standings with the latest ERNIE-5.0-Preview-1103 on LMArena. 🚀 ERNIE-5.0-Preview-1103 holds the top 20 in the most competitive Arena. /blog/posts/ernie-5.0-preview-1120-release-on-lmarena/ Fri, 21 Nov 2025 00:00:00 +0000 /blog/posts/ernie-5.0-preview-1120-release-on-lmarena/ ERNIE-5.0-Preview-1120 now ranks #1 in domestic on the LMArena Vision leaderboard /blog/posts/ernie-4.5-vl-28b-a3b-thinking/ Tue, 11 Nov 2025 00:00:00 +0000 /blog/posts/ernie-4.5-vl-28b-a3b-thinking/ We release ERNIE-4.5-VL-28B-A3B-Thinking, a multimodal reasoning model that achieves SOTA performance while activating only 3B parameters. /blog/posts/ernie-5.0-preview-1022-release-on-lmarena/ Fri, 07 Nov 2025 00:00:00 +0000 /blog/posts/ernie-5.0-preview-1022-release-on-lmarena/ ERNIE-5.0-Preview-1022 now ranks #2 globally on the LMArena Text leaderboard /blog/posts/paddleocr-vl/ Thu, 16 Oct 2025 00:00:00 +0000 /blog/posts/paddleocr-vl/ We are excited to release PaddleOCR-VL, a SOTA and resource-efficient model tailored for document parsing. /blog/posts/plas/ Fri, 12 Sep 2025 00:00:00 +0000 /blog/posts/plas/ How the new PLAS sparse attention update delivers performance gains for long-context inference on ERNIE 4.5 models. /blog/posts/fastdeploy2.0/ Thu, 14 Aug 2025 00:00:00 +0000 /blog/posts/fastdeploy2.0/ As large models such as the ERNIE 4.5 family continue to be open-sourced, interest in their inference performance and deployment efficiency has multiplied across both research and industry. FastDeploy 2.0, built on the PaddlePaddle framework, addresses this demand by offering an end-to-end toolkit for efficient deployment and high-performance inference of large models. /blog/posts/ernie4.5/ Mon, 30 Jun 2025 00:00:00 +0000 /blog/posts/ernie4.5/ We introduce ERNIE 4.5, a new family of large-scale multimodal models comprising 10 distinct variants. The model family consist of Mixture-of-Experts (MoE) models with 47B and 3B active parameters, with the largest model having 424B total parameters, as well as a 0.3B dense model.