HWBench

Intel Core Ultra 7 258V (Lunar Lake) vs Rockchip RK3562 (NPU)

Intel Core Ultra 7 258V (Lunar Lake) is faster in all 3 like-for-like comparisons (largest gap: object detection, 16.24×).

Intel Core Ultra 7 258V (Lunar Lake)Rockchip RK3562 (NPU)
Best object detection300 FPS C
2026-09-27 (page last edited)
57.30 FPS C
2026-10-13 (page last edited)
Powern/an/a
Perf / Wn/an/a
Pricen/an/a
Workloads with data2 of 75 of 7

Best published object detection result per platform (may be from different like-for-like groups — see data). n/a = not published; never estimated.

Show data — all workloads, sources and like-for-like groups

object detection

✓ Like-for-like: model-size class nano (YOLO-n), batch 1. Model, precision and stack may still differ.
PlatformResultModel · precision · stackGradePowerSource
Intel Core Ultra 7 258V (Lunar Lake)300 FPS
inference_time · b=1
YOLO26n
FP32 · Ultralytics + OpenVINO 2026.2.1 · nano (YOLO-n)
Cunknown power n/a
no power published
Ultralytics documentation: Intel OpenVINO integration benchmark
2026-09-27 (page last edited)
Rockchip RK3562 (NPU)57.30 FPS
throughput · b=1
yolov6n
INT8 · RKNN-Toolkit2 / RKNPU (rknn_model_zoo) · nano (YOLO-n)
Cunknown power n/a
no power published
Rockchip rknn_model_zoo README benchmark table
2026-10-13 (page last edited)
✓ Like-for-like: model-size class small (YOLO-s), batch 1. Model, precision and stack may still differ.
PlatformResultModel · precision · stackGradePowerSource
Intel Core Ultra 7 258V (Lunar Lake)251 FPS
inference_time · b=1
YOLO26s
INT8 · Ultralytics + OpenVINO 2026.2.1 · small (YOLO-s)
Cunknown power n/a
no power published
Ultralytics documentation: Intel OpenVINO integration benchmark
2026-09-27 (page last edited)
Rockchip RK3562 (NPU)33.70 FPS
throughput · b=1
yolov5s_relu
INT8 · RKNN-Toolkit2 / RKNPU (rknn_model_zoo) · small (YOLO-s)
Cunknown power n/a
no power published
Rockchip rknn_model_zoo README benchmark table
2026-10-13 (page last edited)
✓ Like-for-like: model-size class medium (YOLO-m), batch 1. Model, precision and stack may still differ.
PlatformResultModel · precision · stackGradePowerSource
Intel Core Ultra 7 258V (Lunar Lake)175 FPS
inference_time · b=1
YOLO26m
INT8 · Ultralytics + OpenVINO 2026.2.1 · medium (YOLO-m)
Cunknown power n/a
no power published
Ultralytics documentation: Intel OpenVINO integration benchmark
2026-09-27 (page last edited)
Rockchip RK3562 (NPU)10.80 FPS
throughput · b=1
yolov5m
INT8 · RKNN-Toolkit2 / RKNPU (rknn_model_zoo) · medium (YOLO-m)
Cunknown power n/a
no power published
Rockchip rknn_model_zoo README benchmark table
2026-10-13 (page last edited)

instance segmentation

Only Rockchip RK3562 (NPU) has published instance segmentation results.

PlatformResultModel · precision · stackGradePowerSource
Rockchip RK3562 (NPU)40.30 FPS
throughput · b=1
yolov5n-seg
INT8 · RKNN-Toolkit2 / RKNPU (rknn_model_zoo) · nano (YOLO-n)
Cunknown power n/a
no power published
Rockchip rknn_model_zoo README benchmark table
2026-10-13 (page last edited)

Intel Core Ultra 7 258V (Lunar Lake):

◌

No published instance segmentation results for Intel Core Ultra 7 258V (Lunar Lake) or Rockchip RK3562 (NPU) yet.
We only show cited public figures — nothing is estimated to fill gaps. Requests tell us what to source or test next.

pose estimation

Only Rockchip RK3562 (NPU) has published pose estimation results.

PlatformResultModel · precision · stackGradePowerSource
Rockchip RK3562 (NPU)32.40 FPS
throughput · b=1
yolov8n-pose
INT8 · RKNN-Toolkit2 / RKNPU (rknn_model_zoo) · nano (YOLO-n)
Cunknown power n/a
no power published
Rockchip rknn_model_zoo README benchmark table
2026-10-13 (page last edited)

Intel Core Ultra 7 258V (Lunar Lake):

◌

No published pose estimation results for Intel Core Ultra 7 258V (Lunar Lake) or Rockchip RK3562 (NPU) yet.
We only show cited public figures — nothing is estimated to fill gaps. Requests tell us what to source or test next.

image classification

Only Rockchip RK3562 (NPU) has published image classification results.

PlatformResultModel · precision · stackGradePowerSource
Rockchip RK3562 (NPU)289 FPS
throughput · b=1
mobilenetv2-12
INT8 · RKNN-Toolkit2 / RKNPU (rknn_model_zoo) · mobile-class CNN
Cunknown power n/a
no power published
Rockchip rknn_model_zoo README benchmark table
2026-10-13 (page last edited)

Intel Core Ultra 7 258V (Lunar Lake):

◌

No published image classification results for Intel Core Ultra 7 258V (Lunar Lake) or Rockchip RK3562 (NPU) yet.
We only show cited public figures — nothing is estimated to fill gaps. Requests tell us what to source or test next.

semantic segmentation

Only Rockchip RK3562 (NPU) has published semantic segmentation results.

PlatformResultModel · precision · stackGradePowerSource
Rockchip RK3562 (NPU)21.00 FPS
throughput · b=1
deeplab-v3-plus-mobilenet-v2
INT8 · RKNN-Toolkit2 / RKNPU (rknn_model_zoo) · mobile-class CNN
Cunknown power n/a
no power published
Rockchip rknn_model_zoo README benchmark table
2026-10-13 (page last edited)

Intel Core Ultra 7 258V (Lunar Lake):

◌

No published semantic segmentation results for Intel Core Ultra 7 258V (Lunar Lake) or Rockchip RK3562 (NPU) yet.
We only show cited public figures — nothing is estimated to fill gaps. Requests tell us what to source or test next.

speech-to-text

◌

No published speech-to-text results for Intel Core Ultra 7 258V (Lunar Lake) or Rockchip RK3562 (NPU) yet.
We only show cited public figures — nothing is estimated to fill gaps. Requests tell us what to source or test next.

LLM generation

Only Intel Core Ultra 7 258V (Lunar Lake) has published LLM generation results.

PlatformResultModel · precision · stackGradePowerSource
Intel Core Ultra 7 258V (Lunar Lake)135 tok/s
2nd-token throughput, input 32 tokens · b=1
minicpm4-0.5b
INT4-MIXED · OpenVINO 2026.4.1 GenAI · LLM ≤4B
Dunknown power n/a
no power published
OpenVINO official LLM benchmarks (llm_models_7-258V.csv)
2026-10-01 (published)

Rockchip RK3562 (NPU):

◌

No published LLM generation results for Rockchip RK3562 (NPU) or Intel Core Ultra 7 258V (Lunar Lake) yet.
We only show cited public figures — nothing is estimated to fill gaps. Requests tell us what to source or test next.

How to read these numbers
Every number is labelled. Confidence: A MLPerf closed, audited · B documented third-party method · C community / review · D vendor-published, not independently verified · E estimate. Power basis: measured with the result · spec vendor spec/envelope · power n/a not published.

Machine-readable: /find.json (see llms.txt); full tables are in “Show data”. Confidence grades: A audited MLPerf closed · B documented third-party · C community · D vendor-published · E estimate. Unknown values are shown as unknown, never estimated. Generated 2026-10-16 from public sources.