AMD Ryzen AI 9 PRO 465 vs AMD Ryzen AI Max 385 Comparison

AMD
AMD

AMD Ryzen AI 9 PRO 465

CORE STATE Gorgon Point
CORE SPECS 10 Cores / 20 Threads
CLOCK SPEED 2 Base / 5 GHz Turbo
CACHE 16 MB
MAX TDP 28W
ARCHITECTURE Zen 5
nm
PROCESS 4 nm
LAUNCH DATE 2026
VS
AMD
AMD

Ryzen AI Max 385

CORE STATE Strix Halo
CORE SPECS 8 Cores / 16 Threads
CLOCK SPEED 3.6 Base / 5 GHz Turbo
CACHE 32 MB (shared)
MAX TDP 55W
ARCHITECTURE Zen 5
nm
PROCESS 4 nm
LAUNCH DATE 2025

PERFORMANCE BENCHMARKS

passmark_data_compression
385,174
406,505
passmark_data_encryption
19,308
19,926
passmark_extended_instructions
26,441
33,873
passmark_find_prime_numbers
126
165
passmark_floating_point_math
66,824
71,105
passmark_integer_math
107,173
107,046
passmark_multithread
31,485
33,705
passmark_physics
1,747
1,889
passmark_random_string_sorting
40,860
43,725
passmark_single_thread
4,168
4,060
passmark_singlethread
4,168
4,060
cinebench_cinebench_r15_multicore
N/A
1,579
cinebench_cinebench_r15_singlecore
N/A
222
cinebench_cinebench_r20_multicore
N/A
6,583
cinebench_cinebench_r20_singlecore
N/A
929
cinebench_cinebench_r23_multicore
N/A
15,674
cinebench_cinebench_r23_singlecore
N/A
2,212

Analysis: AMD Ryzen AI 9 PRO 465 vs AMD Ryzen AI Max 385

FAQ

Q: Which processor has more cores and threads?

A: The AMD Ryzen AI 9 PRO 465 has 10 cores and 20 threads, while the AMD Ryzen AI Max 385 has 8 cores and 16 threads. The PRO 465 carries a 2.00 GHz base clock and a 5.00 GHz boost clock, whereas the Max 385 starts at a higher 3.60 GHz base with the same 5.00 GHz boost.

Q: How much L3 cache does each processor have?

A: The Ryzen AI 9 PRO 465 has 16 MB of L3 cache. The Ryzen AI Max 385 has double that amount, with 32 MB of shared L3 cache. Both share the same per-core L1 (80 KB) and L2 (1 MB) values.

Q: Which chip wins in single-threaded performance?

A: The Ryzen AI 9 PRO 465 scores 4168 in PassMark single-thread tests, which is 2.7% ahead of the Ryzen AI Max 385's score of 4060. The PRO 465 also wins the integer math test by a narrow 0.1% margin, scoring 107173 versus 107046.

Q: Which chip wins in multithreaded performance?

A: The Ryzen AI Max 385 takes the multithread test with a score of 33705, which is 6.6% higher than the PRO 465's 31485. It also wins the data compression test by 5.2% (406505 versus 385174) and the floating-point math test by 6% (71105 versus 66824).

Q: What are the memory bus and bandwidth differences?

A: The Ryzen AI 9 PRO 465 uses a dual-channel memory bus with 89.6 GB/s of bandwidth, while the Ryzen AI Max 385 uses a quad-channel bus with 256.0 GB/s, a substantial margin. The Max 385 also supports ECC memory, which the PRO 465 does not.

Q: How do the two compare in overall benchmark percentile?

A: The Ryzen AI 9 PRO 465 sits at the 93rd percentile among all CPUs, and its nearest rival, the Intel Core Ultra 7 255HX, is 0.4% ahead in average score. The Ryzen AI Max 385 sits at the 88th percentile, with the Intel Core i9-13950HX just 0.1% ahead in average score.

Architecture Differences

Both processors are built on TSMC's 4 nm process node using the Zen 5 architecture, but they belong to different design families. The Ryzen AI 9 PRO 465 comes from the Gorgon Point generation, listed as Ryzen AI PRO 400 with a mix of Zen 5 and Zen 5c cores. The Ryzen AI Max 385 comes from Strix Halo, listed as Ryzen AI Max with Zen 5 cores. This lineage distinction matters for how each chip allocates its resources.

The core counts differ, with the PRO 465 offering 10 cores and 20 threads versus the Max 385's 8 cores and 16 threads. The die layouts also differ significantly. The PRO 465 has a 233 mm² monolithic die, while the Max 385 uses a chiplets arrangement described as 2x 70.6 mm². Both report 80 KB of L1 and 1 MB of L2 per core, but the L3 cache splits: 16 MB for the PRO 465, 32 MB shared for the Max 385. The larger shared L3 pool on the Max 385 helps explain why it performs better in certain cache-sensitive workloads.

Memory architecture separates the two clearly. The PRO 465 supports DDR5 and LPDDR5X over a dual-channel bus with 89.6 GB/s of bandwidth. The Max 385 only supports LPDDR5X but pairs it with a quad-channel bus delivering 256.0 GB/s. That is nearly three times the memory bandwidth, a critical advantage for integrated graphics and data-heavy tasks. The Max 385 also supports ECC memory, a feature absent on the PRO 465.

The integrated GPUs differ as well. The PRO 465 carries a Radeon 890M, while the Max 385 carries a Radeon 8050S. The sockets differ: AMD Socket FP8 for the PRO 465, AMD Socket FP11 for the Max 385. Both use PCIe Gen 4 with 16 lanes for the CPU. The Max 385 has a higher TDP at 55 watts versus 28 watts, and its release date in the database is roughly one year earlier. Neither chip has an unlocked multiplier.

Head-to-Head Benchmarks

The Ryzen AI Max 385 wins 8 of the 11 recorded head-to-head benchmarks. Its largest margin comes in the PassMark find prime numbers test, where it scores 165 versus 126, a 23.6% advantage. The extended instructions test shows a 21.9% gap, with the Max 385 scoring 33873 against the PRO 465's 26441. These two results indicate that the Max 385 handles specialized computational workloads with noticeably more efficiency.

The physics test goes to the Max 385 by 7.5% (1889 versus 1747). The multithread test favors the Max 385 by 6.6% (33705 versus 31485), and the random string sorting test also goes to the Max 385 by 6.6% (43725 versus 40860). The floating-point math test shows a 6% edge for the Max 385 (71105 versus 66824). Data compression goes to the Max 385 by 5.2% (406505 versus 385174), and data encryption by 3.1% (19926 versus 19308).

The Ryzen AI 9 PRO 465 wins the remaining 3 benchmarks. Its single-thread score of 4168 beats the Max 385's 4060 by 2.7%, and the same result appears twice in the database under two test names. The integer math test is nearly a tie, with the PRO 465 scoring 107173 versus 107046, a 0.1% margin that still counts as a win.

The pattern suggests a workload split. The Max 385 dominates in tests that can use its wider memory bus and larger L3 cache, while the PRO 465 holds a smaller but real edge in single-thread and integer operations. The multithread result is notable given that the PRO 465 has more cores and threads, yet still loses by 6.6%, which points to the Max 385's higher base clock and memory subsystem providing the compensating factor.

Specification Differences

The two processors differ across nearly every major specification category. Core count: 10 versus 8. Thread count: 20 versus 16. Base clock: 2.00 GHz versus 3.60 GHz. Boost clock is identical at 5.00 GHz. TDP: 28 watts versus 55 watts. Socket: AMD Socket FP8 versus AMD Socket FP11.

Cache: L3 is 16 MB on the PRO 465 and 32 MB shared on the Max 385. L1 and L2 per core values match at 80 KB and 1 MB respectively. Memory support: DDR5 and LPDDR5X on the PRO 465, LPDDR5X only on the Max 385. Memory bus: dual-channel versus quad-channel. Memory bandwidth: 89.6 GB/s versus 256.0 GB/s. ECC memory: not supported on the PRO 465, supported on the Max 385.

Integrated graphics: Radeon 890M versus Radeon 8050S. Die size: 233 mm² versus 2x 70.6 mm². Generation: Ryzen AI PRO 400 (Zen 5 / Zen 5c) versus Ryzen AI Max (Zen 5, Strix Halo). Codename: Gorgon Point versus Strix Halo. Release date: 2026-01-04 versus 2025-01-05 in the database. Part numbers also differ, as do average benchmark scores: 62498 for the PRO 465 versus 44309 for the Max 385.

The process node, foundry, PCIe configuration, market segment, production status, and multiplier unlock status are identical: 4 nm, TSMC, Gen 4 with 16 lanes, mobile segment, active production, and locked multipliers.

The Verdict

The recorded data shows two processors with different design priorities. The Ryzen AI Max 385 wins the majority of compute benchmarks, including multithread, physics, extended instructions, and prime number tests. Its 256.0 GB/s quad-channel memory bandwidth and 32 MB shared L3 cache give it a structural advantage in memory-intensive workloads. The 55-watt TDP reflects a more aggressive power envelope compared to the PRO 465's 28 watts.

The Ryzen AI 9 PRO 465 counters with a higher single-thread score and a marginal integer math win. Its 10-core, 20-thread configuration does not translate into a multithread victory, as the Max 385 outperforms it by 6.6% in that test. The PRO 465 also holds the higher overall percentile ranking at 93 versus 88, and its average benchmark score of 62498 is significantly higher than the Max 385's 44309.

The percentile and average score gap requires careful reading. The PRO 465 ranks near desktop-class competitors like the Intel Core i9-13900KF, which sits 1.1% ahead in average score. The Max 385 ranks near the Intel Core i9-13950HX and Intel Core Ultra X9 388H. The PRO 465's higher average score comes from strong single-thread and integer results, while the Max 385's lower average reflects its narrower strengths in specialized tests.

Where Each One Wins

The Ryzen AI Max 385 is the choice for workloads that stress the memory subsystem and extended instruction sets. Data compression, encryption, extended instructions, prime number finding, floating-point math, multithread, physics, and random string sorting all go to the Max 385. The 23.6% lead in prime number finding and the 21.9% lead in extended instructions are the largest gaps in the entire comparison. Users running scientific simulations, encryption tasks, or any workload that benefits from 256.0 GB/s of bandwidth will see the Max 385 pull ahead.

The Ryzen AI 9 PRO 465 wins in single-thread performance, integer math, and carries a higher percentile ranking. Its 2.7% single-thread advantage and 0.1% integer math edge indicate a processor that handles general productivity and lightly threaded applications with slightly more responsiveness. The 28-watt TDP also suggests it fits into thinner, more power-conscious mobile designs, while the Max 385's 55-watt TDP points toward larger chassis with more thermal headroom.

The database shows the Max 385 as the stronger all-around compute processor in absolute terms, winning 8 out of 11 benchmarks. The PRO 465 counters with efficiency, a higher percentile standing, and a modest single-thread edge. The choice between them depends on whether the workload favors memory bandwidth and extended instructions or single-thread responsiveness and lower power draw.

DETAILED SPECIFICATIONS

SPECIFICATION
AI 9 PRO 465
AI Max 385
Core Specs
Cores
10
8 -20.0%
Threads
20
16 -20.0%
Base Clock (GHz)
2
3.6 +80.0%
Boost Clock (GHz)
5
5 0.0%
Frequency (GHz)
2
3.6 +80.0%
Turbo Clock (GHz)
5
5 0.0%
Multiplier
20
36 +80.0%
SMP CPUs
1
1 0.0%
Cache
L1 Cache
80 KB (per core)
80 KB (per core)
L2 Cache
1 MB (per core)
1 MB (per core)
L3 Cache
16 MB
32 MB (shared)
Power
TDP (W)
28
55 +96.4%
Configurable TDP
15-54 W
45-120 W
Architecture
Architecture
Zen 5
Zen 5
Codename
Gorgon Point
Strix Halo
Generation
Ryzen AI PRO 400 (Zen 5 / Zen 5c)
Ryzen AI Max (Zen 5 (Strix Halo))
Process Size
4 nm
4 nm
Die Size
233 mm²
2x 70.6 mm²
Foundry
TSMC
TSMC
Memory
Memory Support
DDR5, LPDDR5X
LPDDR5X
Memory Bus
Dual-channel
Quad-channel
Memory Bandwidth
89.6 GB/s
256.0 GB/s
ECC Memory
No
Yes
Platform
Socket
AMD Socket FP8
AMD Socket FP11
PCIe
Gen 4, 16 Lanes(CPU only)
Gen 4, 16 Lanes(CPU only)
Intel Hybrid
Hybrid Cores
4 + 6
—
E-Core Frequency
1400 MHz up to 3.2 GHz
—
AI/NPU
NPU
Yes / 50 TOPS
Yes / 50 TOPS
Graphics
Integrated Graphics
Radeon 890M
Radeon 8050S
Other
Market
Mobile
Mobile
Production Status
Active
Active
Part Number
100-000001862
100-000001424
Package
FP8
FC-BGA
Tj Max
100°C
100°C
View Ryzen AI 9 PRO 465 Details View Ryzen AI Max 385 Details