[DOCS] OV Benchmark update v3

openvinotoolkit · Feb 4, 2025 · 3e9166a · 3e9166a
1 parent ca454c8
commit 3e9166a
Show file tree

Hide file tree

Showing 4 changed files with 288 additions and 567 deletions.
diff --git a/docs/articles_en/about-openvino/performance-benchmarks.rst b/docs/articles_en/about-openvino/performance-benchmarks.rst
@@ -160,7 +160,7 @@ For a listing of all platforms and configurations used for testing, refer to the
 **Disclaimers**
 
 * Intel® Distribution of OpenVINO™ toolkit performance results are based on release
-  2025.0, as of February 05, 2025.
+  2025.0 as of January 28, 2025.
 
 * OpenVINO Model Server performance results are based on release
   2024.5, as of November 20, 2024.

diff --git a/.../articles_en/about-openvino/performance-benchmarks/model-accuracy-int8-fp32.rst b/.../articles_en/about-openvino/performance-benchmarks/model-accuracy-int8-fp32.rst
@@ -66,6 +66,7 @@ the table for more information.
      - -0.09%
      - -0.02%
      - -0.04%
+
 .. list-table:: Model Accuracy for BF16, FP32 and FP16 (FP16: Arc only. BF16: Xeon® 6972P only)
    :header-rows: 1
 
@@ -125,7 +126,8 @@ the table for more information.
      - 0.01%
      - 
      - -0.03%
-.. list-table:: Model Accuracy for AMX-FP16, AMX-INT4, Arc-FP16 and Arc-INT4 (Arc™ A-series)
+
+.. list-table:: Model Accuracy for AMX-FP16, AMX-INT4, Arc-FP16 and Arc-INT4 (Arc™ B-series)
    :header-rows: 1
 
    * - OpenVINO™  Model name
@@ -135,6 +137,13 @@ the table for more information.
      - B, AMX-INT4
      - C, Arc-FP16
      - D, Arc-INT4
+   * - GLM4-9B-Chat
+     - Data Default WWB
+     - Similarity
+     - 6.9%
+     - 3.8%
+     - 6.3%
+     - 15.1%
    * - Qwen-2.5-7B-instruct
      - Data Default WWB
      - Similarity
@@ -209,6 +218,7 @@ the table for more information.
 Notes: For all accuracy metrics a "-", (minus sign), indicates an accuracy drop.
 The Similarity metric is the distance from "perfect" and as such always positive. 
 Similarity is cosine similarity - the dot product of two vectors divided by the product of their lengths.
+
 .. raw:: html
 
    <link rel="stylesheet" type="text/css" href="../../_static/css/benchmark-banner.css">

diff --git a/...rticles_en/about-openvino/performance-benchmarks/performance-benchmarks-faq.rst b/...rticles_en/about-openvino/performance-benchmarks/performance-benchmarks-faq.rst
@@ -63,36 +63,59 @@ Performance Information F.A.Q.
         - Meta AI
         - Auto regressive language
         - 8K
-      * - `Llama-3.2-3B <https://huggingface.co/meta-llama/Llama-3.2-3B-Instruct>`__
+      * - `Llama-3.2-3B-Instruct <https://huggingface.co/meta-llama/Llama-3.2-3B-Instruct>`__
         - Meta AI
         - Auto regressive language
         - 128K
-      * - `Mistral-7b-V0.1 <https://huggingface.co/mistralai/Mistral-7B-v0.1>`__
+      * - `Mistral-7b-Instruct-V0.2 <https://huggingface.co/mistralai/Mistral-7B-v0.2>`__
         - Mistral AI
         - Auto regressive language
-        - 4096
-      * - `Phi3-4k-mini <https://huggingface.co/microsoft/Phi-3-mini-4k-instruct>`__
+        - 32K
+      * - `Phi3-4k-mini-Instruct <https://huggingface.co/microsoft/Phi-3-mini-4k-instruct>`__
         - Huggingface
         - Auto regressive language
         - 4096
       * - `Qwen-2-7B <https://huggingface.co/Qwen/Qwen2-7B>`__
         - Huggingface
         - Auto regressive language
         - 128K
+       * - `Qwen-2.5-7B-Instruct <https://huggingface.co/Qwen/Qwen2.5-7B-Instruct>`__
+        - Huggingface
+        - Auto regressive language
+        - 128K
       * - `Stable-Diffusion-V1-5 <https://huggingface.co/stable-diffusion-v1-5/stable-diffusion-v1-5>`__
         - Hugginface
         - Latent Diffusion Model
         - 77
+      * - `FLUX.1-schnell <https://huggingface.co/black-forest-labs/FLUX.1-schnell>`__
+        - Hugginface
+        - Latent Adversarial Diffusion Distillation Model
+        - 256
       * - `bert-base-cased <https://github.com/PaddlePaddle/PaddleNLP/tree/v2.1.1>`__
         - BERT
         - question / answer
         - 128
+      * - `mask_rcnn_resnet50_atrous_coco <https://github.com/openvinotoolkit/open_model_zoo/tree/master/models/public/mask_rcnn_resnet50_atrous_coco>`__
+        - Mask R-CNN ResNet 50 Atrous
+        - object instance segmentation
+        - 800x1365
+      * - `mobilenet-v2 <https://github.com/openvinotoolkit/open_model_zoo/tree/master/models/public/mobilenet-v2-pytorch>`__
+        - Mobilenet V2 PyTorch
+        - classification
+        - 224x224
+      * - `resnet-50 <https://github.com/openvinotoolkit/open_model_zoo/tree/master/models/public/resnet-50-tf>`__
+        - ResNet-50_v1_ILSVRC-2012
+        - classification
+        - 224x224
+      * - `ssd-resnet34-1200-onnx <https://github.com/openvinotoolkit/open_model_zoo/tree/master/models/public/ssd-resnet34-1200-onnx>`__
+        - ssd-resnet34 onnx model
+        - object detection
+        - 1200x1200
       * - `yolov8n <https://github.com/ultralytics/ultralytics>`__
         - Yolov8nano
         - object detection
         - 608x608
 
-
 .. dropdown:: Where can I purchase the specific hardware used in the benchmarking?
 
    Intel partners with vendors all over the world. For a list of Hardware Manufacturers, see the