diff --git a/docs/articles_en/about-openvino/performance-benchmarks.rst b/docs/articles_en/about-openvino/performance-benchmarks.rst index 31b9c47d93264c..71886581c54c12 100644 --- a/docs/articles_en/about-openvino/performance-benchmarks.rst +++ b/docs/articles_en/about-openvino/performance-benchmarks.rst @@ -158,9 +158,9 @@ For a listing of all platforms and configurations used for testing, refer to the **Disclaimers** * System configurations used for Intel® Distribution of OpenVINO™ toolkit performance results - are based on release 2025.3, as of September 3rd, 2025. + are based on release 2025.4, as of December 1st, 2025. -* OpenVINO Model Server performance results are based on release 2025.3, as of September 3rd, 2025. +* OpenVINO Model Server performance results are based on release 2025.4, as of December 1st, 2025. The results may not reflect all publicly available updates. Intel technologies' features and benefits depend on system configuration and may require enabled hardware, software, or service diff --git a/docs/articles_en/about-openvino/performance-benchmarks/model-accuracy-int8-fp32.rst b/docs/articles_en/about-openvino/performance-benchmarks/model-accuracy-int8-fp32.rst index e9bc7f80939386..63813db86783c2 100644 --- a/docs/articles_en/about-openvino/performance-benchmarks/model-accuracy-int8-fp32.rst +++ b/docs/articles_en/about-openvino/performance-benchmarks/model-accuracy-int8-fp32.rst @@ -41,7 +41,7 @@ the table for more information. * - mobilenet-v2 - ImageNet2012 - accuracy @ top1 - - -0.93% + - -0.91% - -0.93% - -0.91% - -1.03% @@ -96,28 +96,28 @@ the table for more information. - 0.00% - 0.00% - 0.02% - - 0.01% + - 0.02% * - resnet-50 - ImageNet2012 - accuracy @ top1 - 0.00% - 0.00% - 0.00% - - -0.04% + - -0.01% * - ssd-resnet34-1200 - COCO2017_detection_80cl_bkgr - map - 0.02% - 0.02% - 0.02% - - 0.06% + - -0.23% * - yolo_v11 - COCO2017_detection_80cl - AP@0.5:0.05:0.95 - - 0.00% - - 0.00% - - 0.00% - - + - 0.03% + - -2.21% + - -2.21% + - -2.21% .. list-table:: Model Accuracy for AMX-FP16, AMX-INT4, Arc-FP16 and Arc-INT4 (Arc™ B-series) :header-rows: 1 @@ -134,69 +134,62 @@ the table for more information. - 98.1% - 94.4% - 99.5% - - 92.6% + - 94.0% * - DeepSeek-R1-Distill-Qwen-1.5B - Data Default WWB - Similarity - 96.5% - 92.4% - 99.7% - - 92.1% - * - Gemma-3-1B-it + - 92.3% + * - Gemma-3-4B-it - Data Default WWB - Similarity - - 97.3% - 92.0% - - 99.2% - - 91.5% - * - GLM4-9B-Chat - - Data Default WWB - - Similarity - - 98.8% - - 93.3% - - % - - 95.0% + - 83.9% + - + - 84.9% * - Llama-2-7B-chat - Data Default WWB - Similarity - 99.3% - 93.4% - 99.8% - - 91.9% + - 93.4% * - Llama-3-8B - Data Default WWB - Similarity - 98.8% - 94.3% - - % + - 99.7% - 94.5% * - Llama-3.2-3b-instruct - Data Default WWB - Similarity - - 98.2% - - 93.2% - - 98.4% - - 94.0% - * - Mistral-7b-instruct-V0.3 - - Data Default WWB - - Similarity - - 98.3% - - 92.8% - - 99.9% - - 93.6% + - 97.9% + - 94.2% + - 99.7% + - 94.1% * - Phi4-mini-instruct - Data Default WWB - Similarity - - 96.4% - - 92.0% - - 99.3% - - 91.7% + - 89.1% + - 92.1% + - 99.5% + - 92.4% * - Qwen2-VL-7B - Data Default WWB - Similarity - - 97.8% - - 92.4% + - 97.5% + - 88.1% - 99.8% + - 91.4% + * - Qwen3-8B + - Data Default WWB + - Similarity + - 97.8% + - 92.3% + - - 93.0% * - Flux.1-schnell - Data Default WWB @@ -208,10 +201,10 @@ the table for more information. * - Stable-Diffusion-V1-5 - Data Default WWB - Similarity - - 97.3% - - 95.1% + - 96.3% + - 93.3% - 99.5% - - 91.5% + - 93.7% 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. diff --git a/docs/articles_en/about-openvino/performance-benchmarks/performance-benchmarks-faq.rst b/docs/articles_en/about-openvino/performance-benchmarks/performance-benchmarks-faq.rst index f34c563d1a879c..be4fdb480d2c27 100644 --- a/docs/articles_en/about-openvino/performance-benchmarks/performance-benchmarks-faq.rst +++ b/docs/articles_en/about-openvino/performance-benchmarks/performance-benchmarks-faq.rst @@ -55,11 +55,7 @@ Performance Information F.A.Q. - DeepSeek, HF - Auto regressive language - 128K - * - `GLM4-9B-chat `__ - - THUDM - - Transformer - - 128K - * - `Gemma-3-1B-it `__ + * - `Gemma-3-4B-it `__ - Hugginface - Text-To-Text Decoder-only - 128K @@ -75,14 +71,6 @@ Performance Information F.A.Q. - Meta AI - Auto regressive language - 128K - * - `Mistral-7b-Instruct-V0.3 `__ - - Mistral AI - - Auto regressive language - - 32K - * - `Phi3-4k-mini-Instruct `__ - - Huggingface - - Auto regressive language - - 4096 * - `Phi4-mini-Instruct `__ - Huggingface - Auto regressive language diff --git a/docs/sphinx_setup/_static/benchmarks_files/data/graph-data-ovms.json b/docs/sphinx_setup/_static/benchmarks_files/data/graph-data-ovms.json index fbfc802e2b65a1..718862f05614ed 100644 --- a/docs/sphinx_setup/_static/benchmarks_files/data/graph-data-ovms.json +++ b/docs/sphinx_setup/_static/benchmarks_files/data/graph-data-ovms.json @@ -9,10 +9,10 @@ "throughput": { "Precisions": [ { - "fp32_ov": 161.753, - "fp32_ovms": 159.282, - "int8_ov": 411.774, - "int8_ovms": 406.262 + "fp32_ov": 161.421, + "fp32_ovms": 159.692, + "int8_ov": 410.288, + "int8_ovms": 405.436 } ], "Unit": "FPS", @@ -22,7 +22,7 @@ }, { "Platform": "Intel® Xeon® Gold 6238M", - "Model": "detectron_COCO-InstanceSegmentation_mask_rcnn_R_50_FPN_3x", + "Model": "detectron-v2_mask_rcnn_r_50_fpn_3x", "featured_SKU": false, "whats_new_model": false, "PlatformType": "Server Platforms (Intel® Xeon®)", @@ -30,10 +30,10 @@ "throughput": { "Precisions": [ { - "fp32_ov": 14.741, - "fp32_ovms": 14.687, - "int8_ov": 42.481, - "int8_ovms": 41.398 + "fp32_ov": 14.704, + "fp32_ovms": 14.639, + "int8_ov": 42.484, + "int8_ovms": 41.347 } ], "Unit": "FPS", @@ -43,7 +43,7 @@ }, { "Platform": "Intel® Xeon® Gold 6238M", - "Model": "manual_yolo11", + "Model": "yolo11", "featured_SKU": false, "whats_new_model": false, "PlatformType": "Server Platforms (Intel® Xeon®)", @@ -51,10 +51,10 @@ "throughput": { "Precisions": [ { - "fp32_ov": 368.973, - "fp32_ovms": 253.242, - "int8_ov": 778.246, - "int8_ovms": 506.974 + "fp32_ov": 369.376, + "fp32_ovms": 253.031, + "int8_ov": 764.138, + "int8_ovms": 502.462 } ], "Unit": "FPS", @@ -72,10 +72,10 @@ "throughput": { "Precisions": [ { - "fp32_ov": 3275.067, - "fp32_ovms": 2816.773, - "int8_ov": 10250.761, - "int8_ovms": 7413.038 + "fp32_ov": 3262.177, + "fp32_ovms": 2798.412, + "int8_ov": 10232.437, + "int8_ovms": 7391.948 } ], "Unit": "FPS", @@ -93,10 +93,10 @@ "throughput": { "Precisions": [ { - "fp32_ov": 575.657, - "fp32_ovms": 566.718, - "int8_ov": 2133.572, - "int8_ovms": 2033.518 + "fp32_ov": 575.297, + "fp32_ovms": 566.918, + "int8_ov": 2132.579, + "int8_ovms": 2033.443 } ], "Unit": "FPS", @@ -114,10 +114,10 @@ "throughput": { "Precisions": [ { - "fp32_ov": 10.601, - "fp32_ovms": 10.439, - "int8_ov": 40.444, - "int8_ovms": 38.375 + "fp32_ov": 10.539, + "fp32_ovms": 10.406, + "int8_ov": 40.369, + "int8_ovms": 38.329 } ], "Unit": "FPS", @@ -135,10 +135,10 @@ "throughput": { "Precisions": [ { - "fp32_ov": 182.13, - "fp32_ovms": 182.49, - "int8_ov": 467.737, - "int8_ovms": 460.009 + "fp32_ov": 184.277, + "fp32_ovms": 182.473, + "int8_ov": 468.414, + "int8_ovms": 461.101 } ], "Unit": "FPS", @@ -148,7 +148,7 @@ }, { "Platform": "Intel® Xeon® Platinum 8260M", - "Model": "detectron_COCO-InstanceSegmentation_mask_rcnn_R_50_FPN_3x", + "Model": "detectron-v2_mask_rcnn_r_50_fpn_3x", "featured_SKU": false, "whats_new_model": false, "PlatformType": "Server Platforms (Intel® Xeon®)", @@ -156,10 +156,10 @@ "throughput": { "Precisions": [ { - "fp32_ov": 16.853, - "fp32_ovms": 16.814, - "int8_ov": 48.434, - "int8_ovms": 47.129 + "fp32_ov": 16.91, + "fp32_ovms": 16.827, + "int8_ov": 48.603, + "int8_ovms": 47.216 } ], "Unit": "FPS", @@ -169,7 +169,7 @@ }, { "Platform": "Intel® Xeon® Platinum 8260M", - "Model": "manual_yolo11", + "Model": "yolo11", "featured_SKU": false, "whats_new_model": false, "PlatformType": "Server Platforms (Intel® Xeon®)", @@ -177,10 +177,10 @@ "throughput": { "Precisions": [ { - "fp32_ov": 416.429, - "fp32_ovms": 287.978, - "int8_ov": 856.243, - "int8_ovms": 541.99 + "fp32_ov": 418.307, + "fp32_ovms": 286.944, + "int8_ov": 863.093, + "int8_ovms": 540.621 } ], "Unit": "FPS", @@ -198,10 +198,10 @@ "throughput": { "Precisions": [ { - "fp32_ov": 3778.861, - "fp32_ovms": 3214.536, - "int8_ov": 12084.817, - "int8_ovms": 7584.17 + "fp32_ov": 3814.957, + "fp32_ovms": 3204.445, + "int8_ov": 12062.483, + "int8_ovms": 7549.961 } ], "Unit": "FPS", @@ -219,10 +219,10 @@ "throughput": { "Precisions": [ { - "fp32_ov": 638.215, - "fp32_ovms": 637.338, - "int8_ov": 2421.012, - "int8_ovms": 2323.254 + "fp32_ov": 646.097, + "fp32_ovms": 639.84, + "int8_ov": 2426.95, + "int8_ovms": 2326.988 } ], "Unit": "FPS", @@ -240,10 +240,10 @@ "throughput": { "Precisions": [ { - "fp32_ov": 12.094, - "fp32_ovms": 11.884, - "int8_ov": 46.873, - "int8_ovms": 43.57 + "fp32_ov": 12.134, + "fp32_ovms": 11.918, + "int8_ov": 47.041, + "int8_ovms": 43.73 } ], "Unit": "FPS", @@ -261,10 +261,10 @@ "throughput": { "Precisions": [ { - "fp32_ov": 35.668, - "fp32_ovms": 34.549, - "int8_ov": 100.71, - "int8_ovms": 99.968 + "fp32_ov": 35.39, + "fp32_ovms": 34.572, + "int8_ov": 100.727, + "int8_ovms": 99.353 } ], "Unit": "FPS", @@ -274,7 +274,7 @@ }, { "Platform": "Intel® Core™ i9-11900K", - "Model": "detectron_COCO-InstanceSegmentation_mask_rcnn_R_50_FPN_3x", + "Model": "detectron-v2_mask_rcnn_r_50_fpn_3x", "featured_SKU": false, "whats_new_model": false, "PlatformType": "Client Platforms (Intel® Core™)", @@ -282,10 +282,10 @@ "throughput": { "Precisions": [ { - "fp32_ov": 3.097, - "fp32_ovms": 3.106, - "int8_ov": 10.316, - "int8_ovms": 10.186 + "fp32_ov": 3.096, + "fp32_ovms": 3.108, + "int8_ov": 10.207, + "int8_ovms": 10.148 } ], "Unit": "FPS", @@ -295,7 +295,7 @@ }, { "Platform": "Intel® Core™ i9-11900K", - "Model": "manual_yolo11", + "Model": "yolo11", "featured_SKU": false, "whats_new_model": false, "PlatformType": "Client Platforms (Intel® Core™)", @@ -303,10 +303,10 @@ "throughput": { "Precisions": [ { - "fp32_ov": 83.783, - "fp32_ovms": 70.678, - "int8_ov": 210.296, - "int8_ovms": 134.698 + "fp32_ov": 83.682, + "fp32_ovms": 70.552, + "int8_ov": 209.445, + "int8_ovms": 134.132 } ], "Unit": "FPS", @@ -324,10 +324,10 @@ "throughput": { "Precisions": [ { - "fp32_ov": 867.169, - "fp32_ovms": 737.016, - "int8_ov": 2680.265, - "int8_ovms": 2139.983 + "fp32_ov": 864.265, + "fp32_ovms": 734.701, + "int8_ov": 2668.255, + "int8_ovms": 2130.51 } ], "Unit": "FPS", @@ -345,10 +345,10 @@ "throughput": { "Precisions": [ { - "fp32_ov": 116.026, - "fp32_ovms": 113.814, - "int8_ov": 455.32, - "int8_ovms": 439.632 + "fp32_ov": 116.497, + "fp32_ovms": 113.591, + "int8_ov": 454.619, + "int8_ovms": 438.959 } ], "Unit": "FPS", @@ -366,10 +366,10 @@ "throughput": { "Precisions": [ { - "fp32_ov": 2.004, - "fp32_ovms": 2.03, + "fp32_ov": 2.002, + "fp32_ovms": 2.028, "int8_ov": 7.829, - "int8_ovms": 7.8 + "int8_ovms": 7.798 } ], "Unit": "FPS", @@ -387,10 +387,10 @@ "throughput": { "Precisions": [ { - "fp32_ov": 16.841, - "fp32_ovms": 16.644, - "int8_ov": 14.296, - "int8_ovms": 14.218 + "fp32_ov": 16.436, + "fp32_ovms": 16.377, + "int8_ov": 14.186, + "int8_ovms": 14.103 } ], "Unit": "FPS", @@ -400,7 +400,7 @@ }, { "Platform": "Intel® Core™ i3-10100", - "Model": "detectron_COCO-InstanceSegmentation_mask_rcnn_R_50_FPN_3x", + "Model": "detectron-v2_mask_rcnn_r_50_fpn_3x", "featured_SKU": false, "whats_new_model": false, "PlatformType": "Client Platforms (Intel® Core™)", @@ -408,10 +408,10 @@ "throughput": { "Precisions": [ { - "fp32_ov": 1.396, - "fp32_ovms": 1.447, - "int8_ov": 2.535, - "int8_ovms": 2.564 + "fp32_ov": 1.412, + "fp32_ovms": 1.435, + "int8_ov": 2.575, + "int8_ovms": 2.578 } ], "Unit": "FPS", @@ -421,7 +421,7 @@ }, { "Platform": "Intel® Core™ i3-10100", - "Model": "manual_yolo11", + "Model": "yolo11", "featured_SKU": false, "whats_new_model": false, "PlatformType": "Client Platforms (Intel® Core™)", @@ -429,10 +429,10 @@ "throughput": { "Precisions": [ { - "fp32_ov": 40.77, - "fp32_ovms": 35.227, - "int8_ov": 72.885, - "int8_ovms": 55.94 + "fp32_ov": 41.381, + "fp32_ovms": 35.024, + "int8_ov": 72.493, + "int8_ovms": 55.616 } ], "Unit": "FPS", @@ -450,10 +450,10 @@ "throughput": { "Precisions": [ { - "fp32_ov": 436.567, - "fp32_ovms": 372.626, - "int8_ov": 711.324, - "int8_ovms": 612.642 + "fp32_ov": 430.69, + "fp32_ovms": 367.515, + "int8_ov": 707.573, + "int8_ovms": 608.902 } ], "Unit": "FPS", @@ -471,10 +471,10 @@ "throughput": { "Precisions": [ { - "fp32_ov": 55.271, - "fp32_ovms": 54.504, - "int8_ov": 117.911, - "int8_ovms": 113.747 + "fp32_ov": 55.216, + "fp32_ovms": 54.15, + "int8_ov": 117.168, + "int8_ovms": 113.079 } ], "Unit": "FPS", @@ -492,10 +492,10 @@ "throughput": { "Precisions": [ { - "fp32_ov": 0.99, - "fp32_ovms": 1.015, - "int8_ov": 1.947, - "int8_ovms": 1.951 + "fp32_ov": 0.98, + "fp32_ovms": 1.0, + "int8_ov": 1.936, + "int8_ovms": 1.943 } ], "Unit": "FPS", diff --git a/docs/sphinx_setup/_static/download/benchmarking_OV_platform_list.pdf b/docs/sphinx_setup/_static/download/benchmarking_OV_platform_list.pdf index 7920e3f10373db..5c1f2e68212f36 100644 Binary files a/docs/sphinx_setup/_static/download/benchmarking_OV_platform_list.pdf and b/docs/sphinx_setup/_static/download/benchmarking_OV_platform_list.pdf differ diff --git a/docs/sphinx_setup/_static/download/benchmarking_OV_system_info_detailed.xlsx b/docs/sphinx_setup/_static/download/benchmarking_OV_system_info_detailed.xlsx index d4334423d65fa4..bdb65d1fccfd28 100644 --- a/docs/sphinx_setup/_static/download/benchmarking_OV_system_info_detailed.xlsx +++ b/docs/sphinx_setup/_static/download/benchmarking_OV_system_info_detailed.xlsx @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:a2a90960620f45e00c60adba9c29d6c7fd75219d4a3bddc103ebb5001f1c1e35 -size 74279 +oid sha256:224d139c3c4267d4d6459a61580d17fe9bd1aa39453bd83eafc512a9af2650d3 +size 61867