Home / Mali-G925-Immortalis MC11 / Compare

Mali-G925-Immortalis MC12 vs Mali-G925-Immortalis MC12

On Mali-G925-Immortalis MC11 (POCO X8 Pro Max, REDMI Turbo 5 Max, Samsung Galaxy Tab S11 Ultra, vivo X200s, Xiaomi 15T Pro). The first driver named is compared against the second, which is the baseline.

StockMali-G925-Immortalis MC12v1.r49p1-03bet0.bc90a72cfac7e7049eb7f4a59891303a

CustomMali-G925-Immortalis MC12v1.r49p1-03bet0.f8a98b506b89b21c80a508d70abfcb3f

Graphics system version (Vulkan)1.3.278 to 1.3.278

Optional features (extensions)151 to 152+1 -0

Features that pass their check (validated)53 to 400 pass only on Mali-G925-Immortalis MC12 13 pass only on Mali-G925-Immortalis MC12

Speed test scenes (benchmark)5 faster 0 slower44% faster overall (geometric mean)

Games each driver could run (an estimate from its feature list): green likely, yellow maybe, orange limited, red no

StockDX92002+DX102006+DX112009+DX122015+Switch

CustomDX92002+DX102006+DX112009+DX122015+Switch

compute_nbody15% faster
hdr_2160p43% faster
oit_linked_lists55% faster
pipeline_barriers_2160p59% faster
subpasses_2160p50% faster

Custom driver against stock, per scene. Bars to the right are faster, to the left slower.

Mali-G925-Immortalis MC12 details Mali-G925-Immortalis MC12 details

Feature checks that differ (14)

Feature	Stock	Mali-G925-Immortalis MC12	Change
depthClamp VkPhysicalDeviceFeatures	pass	untested	lost
largePoints VkPhysicalDeviceFeatures	pass	untested	lost
compat.helper_loop_terminator core	pass	fail	lost
core.blend_advertised_formats core	pass	untested	lost
core.compute_big_stack core	pass	untested	lost
core.host_coherent_readback core	pass	untested	lost
core.mrt_partial_kill core	pass	untested	lost
core.ubo_update_buffer core	pass	untested	lost
core.ubo_written_after_record core	pass	untested	lost
core.varying_subset core	pass	untested	lost
mem.image_padding core	pass	untested	lost
stage.geometry_max_output core	pass	untested	lost
sync.first_submit_clear_then_compute core	pass	untested	lost
stage.geometry_point_size core	unsupported	untested	changed

Speed test scenes (benchmark)

The two drivers were not measured on the same set of device models. Frame times from different devices do not compare drivers, so read these numbers with that in mind.

Scene	Stock ms	Mali-G925-Immortalis MC12 ms	Difference	Starts	GPU clock, MHz	Picture vs stock
compute_nbody	12.45 typical 12.41	10.80 typical 10.60	15% faster	3 of 3 vs 3 of 3	? vs ? clock unknown	no large difference 0.0 no small difference worst 0.0 64x36
hdr_2160p	11.98 typical 11.70	8.39 typical 8.27	43% faster	3 of 3 vs 3 of 3	? vs ? clock unknown	no large difference 0.0 no small difference worst 0.0 64x36
oit_linked_lists	20.38 typical 20.46	13.17 typical 13.39	55% faster	3 of 3 vs 3 of 3	? vs ? clock unknown	no large difference 0.0 no small difference worst 0.0 64x36
pipeline_barriers	5.95 typical 5.80	5.66 typical 5.61	too light, see pipeline_barriers_2160p	3 of 3 vs 3 of 3	? vs ? clock unknown	no large difference 0.0 no small difference worst 0.0 64x36
pipeline_barriers_2160p	9.71 typical 9.72	6.09 typical 6.22	59% faster	3 of 3 vs 3 of 3	? vs ? clock unknown	no large difference 0.0 no small difference worst 0.0 64x36
subpasses	n/a	7.39	too light, see subpasses_2160p	3 of 3 vs 3 of 3	? vs ? clock unknown	not checked
subpasses_2160p	14.78 typical 14.76	9.86 typical 9.84	50% faster	3 of 3 vs 3 of 3	? vs ? clock unknown	not checked

Time to draw one frame, per scene: the average (mean) frame time of the scene's best round, which is how many frames the driver delivered; lower is faster. "Typical" beside it is the median frame, which can sit well under the average when a driver's frames come in two speeds. A pair of reports made before per-round averages were recorded is compared on the median. A scene whose rounds disagree by more than 15% is left out. A scene marked "paced" was held at that mean frame time by the driver or the display queue, together with at least one other scene of the same run; its time says how the frames were spaced, not how fast the driver rendered, so it is not compared. A scene marked "too light" took under 8 ms at the standard size (1920 by 1080) on both drivers, where the screen's frame queue spaces the frames more than the chip does; its heavier run is the one compared: the row ending in _2160p is the scene drawn at 3840 by 2160, and compute_nbody_2x is that scene with twice the particles. "Faster" and "slower" describe Mali-G925-Immortalis MC12 against Mali-G925-Immortalis MC12. "Picture vs stock" compares one fixed frame per scene as a coarse colour grid (0 is identical, above 40 is a different picture); it finds a scene that was not drawn. Where both reports carry the finer 64x36 grid, the second figure is how many of its 2,304 cells differ by more than 4 of 255, and "worst" is the largest single cell; this is what finds a small rendering error in a picture that otherwise matches. A row marked 16x9 comes from a report made before the finer grid existed. "Starts" is how many of a scene's process starts reached a measured round. A GPU clock marked "not comparable" differed by more than 5% of the device's maximum between the two timings.

Technical differences (Vulkan)

Extensions only in Mali-G925-Immortalis MC12 (1)

VK_EXT_hdr_metadata

Extensions only in Mali-G925-Immortalis MC12 (0)

None

Core features that differ (0)

None

Limits that differ (0)

Limit	Stock	Mali-G925-Immortalis MC12

Formats supported by only one driver (0 gained, 0 lost)

Only in Mali-G925-Immortalis MC12:

None

Only in Mali-G925-Immortalis MC12:

None