# Geekbench Hacker Approved page: https://hackerapproved.com/p/geekbench/ 11 people recommended Geekbench in Hacker News comments, 5 had mixed feelings and 23 criticized it, November 2025 to October 2026. It was recommended in 6 of 12 months, in 8 threads. It does not meet the Hacker Approved badge rule. **Verdict:** Criticized more than recommended, mainly for multi-core scores are often misused as general performance measures; those who recommend it see it as a cross-platform benchmark that tracks SPEC closely and mixes single-core and multi-core tests. Summary written by Claude from the comments below. ## What people warn about - Weak link to real-world performance (4 comments in the sample): "The Geekbench multi-threaded results do not provide any useful information about how a computer will behave for such applications." ([source](https://news.ycombinator.com/item?id=49038570)) "I just don't believe these geekbench numbers represent real world performance numbers" ([source](https://news.ycombinator.com/item?id=47431721)) "Geekbench results do not reflect at all the performance of such applications" ([source](https://news.ycombinator.com/item?id=47279658)) - Poor multi-core scaling (3 comments in the sample): "It has nothing to do with Geekbench 6 being a surprisingly bad benchmark, especially for big CPUs." ([source](https://news.ycombinator.com/item?id=47293322)) "The scaling is atrocious, even for tasks that should be extremely parallelizable." ([source](https://news.ycombinator.com/item?id=47293058)) "Geekbench 5 is famously much better than Geekbench 6 for benchmarking these workstation-class CPUs" ([source](https://news.ycombinator.com/item?id=49025983)) - Results tuned or gamed (3 comments in the sample): "Geekbench can be gamed by CPU vendors." ([source](https://news.ycombinator.com/item?id=49037142)) "They tuned (the last version of their) benchmark specifically to give better numbers on hardware that tends to throttle under performance load." ([source](https://news.ycombinator.com/item?id=49768708)) "Both that and the SPEC compiler shenanigans are cheating by changing the test" ([source](https://news.ycombinator.com/item?id=47918069)) - Multi-core test scope too narrow (2 comments in the sample): "Including workloads that are almost entirely single-threaded does not tell you anything about the "multi-core" performance of the processor." ([source](https://news.ycombinator.com/item?id=49030021)) "The Geekbench 5 approach of pretending Amdahl's Law doesn't exist is sometimes a valid benchmarking strategy" ([source](https://news.ycombinator.com/item?id=49026252)) ## Why people recommend it - Broad, realistic workloads (4 comments in the sample): "I like Geekbench's approach of combining general and specialized tests to reward CPUs for being well-rounded" ([source](https://news.ycombinator.com/item?id=46623319)) "GeekBench probably made the right choice to optimize for more realistic real-world workloads" ([source](https://news.ycombinator.com/item?id=47292091)) "it has a bunch of workloads, unlike many other benchmarks like cinebench for example" ([source](https://news.ycombinator.com/item?id=47293342)) - Tracks SPEC results closely (3 comments in the sample): "the benchmarks are quite consistent, even across platforms, and track SPEC results fairly accurately" ([source](https://news.ycombinator.com/item?id=49431496)) "Geekbench 5 and 6 both correlated with SPEC scores at nearly 1:1." ([source](https://news.ycombinator.com/item?id=49029296)) "geekbench corresponding very closely to SPEC as well" ([source](https://news.ycombinator.com/item?id=49659361)) - Good general CPU performance proxy (3 comments in the sample): "Personally I think Geekbench is a pretty damn good consumer testing benchmarks." ([source](https://news.ycombinator.com/item?id=49032580)) "Geekbench is extremely good at showing general CPU performance, especially ST." ([source](https://news.ycombinator.com/item?id=49029368)) "I believe it's an excellent proxy for general performance of a CPU" ([source](https://news.ycombinator.com/item?id=49026366)) - Only consumer cross-platform benchmark (1 comment in the sample): "Geekbench is the only consumer usable cross-platform benchmark" ([source](https://news.ycombinator.com/item?id=49423378)) ## Where to get it - [Visit the official site](https://www.geekbench.com/) ## The badge A product earns the Hacker Approved badge when at least 10 people recommend it, recommenders outnumber critics at least 2 to 1 (mixed feelings count toward neither side), it was recommended in at least 4 of the 12 months and in at least 5 different threads, and no single thread supplies more than half of the people who recommend it. Health and money products are never badged. ## Cite as Hacker Approved, "Geekbench", https://hackerapproved.com/p/geekbench/ (11 recommend, 5 mixed, 23 criticize; Hacker News comments, November 2025 to October 2026). Counts updated 3 Nov 2026, with data through October 31, 2026.