←back to thread

1080 points antipaul | 2 comments | | HN request time: 0.545s | source
Show context
WoodenChair ◴[] No.25065476[source]
Their line from the video about being the highest performance chip in single core appears to be true. This is of course a synthetic benchmark but the single core result is very promising. Note that the single core and multi core scores exceed the top-of-the-line 16” MacBook Pro (9th generation 8-core i9 2.4 ghz). I actually made the call to sell my 16” for the new Air yesterday. It’s looking like a good call. Glad I’m selling my 16” while it still has some value.

You can see all Air results so far here: https://browser.geekbench.com/v5/cpu/search?q=MacBookAir10%2...

replies(8): >>25065492 #>>25065503 #>>25065568 #>>25065571 #>>25065783 #>>25066300 #>>25066486 #>>25069168 #
1. minxomat ◴[] No.25065568[source]
Direct comparison between best MBP Intel 16" vs M1 Air: https://browser.geekbench.com/v5/cpu/compare/4651916?baselin...

1.5x single-core perf.

M1 MacBook Pro vs Intel MBP (top specs) show same performance: https://browser.geekbench.com/v5/cpu/compare/4652718?baselin...

Likely because GB5 doesn't run long enough to trigger thermal throttling on the M1 MBA.

M1 is beating all CPUs on the market in single-core scores: https://browser.geekbench.com/processor-benchmarks (M1 at 1719, vs AMD Ryzen 9 5950X at 1628).

Anandtech on the memory-affinity of GeekBench vs SPEC:

> There’s been a lot of criticism about more common benchmark suites such as GeekBench, but frankly I've found these concerns or arguments to be quite unfounded. The only factual differences between workloads in SPEC and workloads in GB5 is that the latter has less outlier tests which are memory-heavy, meaning it’s more of a CPU benchmark whereas SPEC has more tendency towards CPU+DRAM.

replies(1): >>25065636 #
2. cmer ◴[] No.25065636[source]
The new MBA is a total beast. The comparison is almost unbelievable. Can't wait to see what they do with the iMac, Mac Pro and MBP 16". Just phenomenal!