European benchmarks are mostly higher after Asian benchmarks finished lower, as concerns over leadership at chipmaker Nvidia weigh on artificial intelligence-related stocks.
World shares are mixed as Nvidia's troubles weigh on AI stocks
European benchmarks are mostly higher after Asian benchmarks finished lower, as concerns over leadership at chipmaker Nvidia weigh on artificial intelligence-related stocks.
bit.ly
November 12, 2026 at 11:30 AM
European benchmarks are mostly higher after Asian benchmarks finished lower, as concerns over leadership at chipmaker Nvidia weigh on artificial intelligence-related stocks.
"Take the frame-gen stats OUT of the benchmarks."
November 12, 2026 at 8:11 PM
"Take the frame-gen stats OUT of the benchmarks."
Looks like Fable 5.2 is above the already steep trendline on three of the most informative unsaturated benchmarks (ECI is a composite of other benchmarks, Remote Labor measures the ability to do end-to-end freelance jobs, RoboDojo involves controlling robotics).
November 10, 2026 at 3:49 AM
Looks like Fable 5.2 is above the already steep trendline on three of the most informative unsaturated benchmarks (ECI is a composite of other benchmarks, Remote Labor measures the ability to do end-to-end freelance jobs, RoboDojo involves controlling robotics).
Apple Silicon Benchmarks
Neat interactive website for comparing Geekbench 6/7 and Cinebench scores across Apple's M1 through M6 chips.
bpetrynski.github.io/apple-m-...
Neat interactive website for comparing Geekbench 6/7 and Cinebench scores across Apple's M1 through M6 chips.
bpetrynski.github.io/apple-m-...
November 12, 2026 at 5:35 PM
Apple Silicon Benchmarks
Neat interactive website for comparing Geekbench 6/7 and Cinebench scores across Apple's M1 through M6 chips.
bpetrynski.github.io/apple-m-...
Neat interactive website for comparing Geekbench 6/7 and Cinebench scores across Apple's M1 through M6 chips.
bpetrynski.github.io/apple-m-...
I have my own set of benchmarks here:
bsky.app/profile/null...
is there room for macro benchmarks?
how to we rationalize different approaches to benchmarks?
bsky.app/profile/null...
is there room for macro benchmarks?
how to we rationalize different approaches to benchmarks?
Who's got frontend frameworks?
Trying to collect some stats on update efficiency
(rather than rendering new dom en-masse
(which js-framework-benchmark heavily favors <3))
Trying to collect some stats on update efficiency
(rather than rendering new dom en-masse
(which js-framework-benchmark heavily favors <3))
November 10, 2026 at 9:40 PM
I have my own set of benchmarks here:
bsky.app/profile/null...
is there room for macro benchmarks?
how to we rationalize different approaches to benchmarks?
bsky.app/profile/null...
is there room for macro benchmarks?
how to we rationalize different approaches to benchmarks?
Michael Saylor call your office
Strategy Inc. shares fall 6.4% in premarket trading as MSCI Inc. is dropping the Bitcoin treasury firm from its global equity benchmarks effective Nov. 30.
Strategy Inc. shares fall 6.4% in premarket trading as MSCI Inc. is dropping the Bitcoin treasury firm from its global equity benchmarks effective Nov. 30.
November 12, 2026 at 1:17 PM
Michael Saylor call your office
Strategy Inc. shares fall 6.4% in premarket trading as MSCI Inc. is dropping the Bitcoin treasury firm from its global equity benchmarks effective Nov. 30.
Strategy Inc. shares fall 6.4% in premarket trading as MSCI Inc. is dropping the Bitcoin treasury firm from its global equity benchmarks effective Nov. 30.
Meanwhile, Nithya is nearly up to 9.5%. I want her to get above 10 just to make my pre-election benchmarks extremely accurate lol.
November 10, 2026 at 3:31 AM
Meanwhile, Nithya is nearly up to 9.5%. I want her to get above 10 just to make my pre-election benchmarks extremely accurate lol.
[sweetly to an llm] wow youre so token efficent. i have a good idea what servers have the answers to your benchmarks.
November 9, 2026 at 3:57 AM
[sweetly to an llm] wow youre so token efficent. i have a good idea what servers have the answers to your benchmarks.
Oh totes forgot questionable performance benchmarks
November 11, 2026 at 5:17 AM
Oh totes forgot questionable performance benchmarks
Opus 5.5 otoh was happy to get a couple of things wrong on the official benchmarks just to fit in.
November 11, 2026 at 9:58 AM
Opus 5.5 otoh was happy to get a couple of things wrong on the official benchmarks just to fit in.
that post is so old i should release new benchmarks...
November 10, 2026 at 8:54 AM
that post is so old i should release new benchmarks...
They have a huge amount of potential but very, very bad internal benchmarks
November 11, 2026 at 10:10 AM
They have a huge amount of potential but very, very bad internal benchmarks
How Agent Anomaly Detection scores on benchmarks we didn't write #googlecloud #ai https://developers.googleblog.com/how-agent-anomaly-detection-scores-on-benchmarks-we-didnt-write/
How Agent Anomaly Detection scores on benchmarks we didn't write- Google Developers Blog
developers.googleblog.com
November 12, 2026 at 7:30 PM
How Agent Anomaly Detection scores on benchmarks we didn't write #googlecloud #ai https://developers.googleblog.com/how-agent-anomaly-detection-scores-on-benchmarks-we-didnt-write/
Revisiting this as, thus far in the count, Nithya has gained 11.2 points on Bass from first drop to latest drop (with vote still left to count). Feel very vindicated in my pre-election benchmarks for the first drop. (especially as some said Bass should feel safe with a 10pt lead - clearly not!)
Nithya -5: We’re gonna win.
Nithya -10: We’re likely to win, but I’ll be anxious.
Nithya -15: Gonna be a nailbiter, sweating bullets for days.
Nithya -20 or more: Not looking good, fam.
Nithya even or ahead: lol. lmao.
Nithya -10: We’re likely to win, but I’ll be anxious.
Nithya -15: Gonna be a nailbiter, sweating bullets for days.
Nithya -20 or more: Not looking good, fam.
Nithya even or ahead: lol. lmao.
November 11, 2026 at 5:25 AM
Revisiting this as, thus far in the count, Nithya has gained 11.2 points on Bass from first drop to latest drop (with vote still left to count). Feel very vindicated in my pre-election benchmarks for the first drop. (especially as some said Bass should feel safe with a 10pt lead - clearly not!)
UK House Rebuild & Construction Cost Benchmarks (2026 Summary)
buildingcosts.leaflet.pub
November 12, 2026 at 11:48 AM
Explore all looping methods in C#: list iteration techniques ranked by performance with benchmarks.
#oop #gamedev #indiedev #csharp #gamedevelopment
#oop #gamedev #indiedev #csharp #gamedevelopment
How to Loop Through a List in C#: Every Way, Benchmarked
How to loop through and iterate a List<T> in C# with foreach, for, ForEach, Index(), and spans, plus break, continue, safe removal, and benchmarks.
khalidabuhakmeh.com
November 10, 2026 at 2:11 PM
Explore all looping methods in C#: list iteration techniques ranked by performance with benchmarks.
#oop #gamedev #indiedev #csharp #gamedevelopment
#oop #gamedev #indiedev #csharp #gamedevelopment
November 11, 2026 at 12:00 PM
Nach gerade einmal zwei Wochen Testphase wird ein Multi-Agenten-System für anspruchsvolle Aufgaben auf die Menschheit losgelassen?
Habt ihr eigentlich noch alle Tassen im Schrank?
the-decoder.de/google-start...
Habt ihr eigentlich noch alle Tassen im Schrank?
the-decoder.de/google-start...
Google startet Gemini 4 Carbon mit neuer Agenten-Schwarm-Funktion
Google macht Gemini 4 Carbon nach zweiwöchiger Testphase allgemein verfügbar. Das Modell übernimmt in mehreren Benchmarks die Spitze, teils vor Anthropics neuem Fable 5.2, und arbeitet dabei deutlich ...
the-decoder.de
November 10, 2026 at 7:01 PM
Nach gerade einmal zwei Wochen Testphase wird ein Multi-Agenten-System für anspruchsvolle Aufgaben auf die Menschheit losgelassen?
Habt ihr eigentlich noch alle Tassen im Schrank?
the-decoder.de/google-start...
Habt ihr eigentlich noch alle Tassen im Schrank?
the-decoder.de/google-start...
My first job at college was minimum 60 hour weeks until you hit a bunch of benchmarks (typically two years)
You’ll be shocked* to learn the attrition rate
You’ll be shocked* to learn the attrition rate
November 12, 2026 at 2:27 PM
My first job at college was minimum 60 hour weeks until you hit a bunch of benchmarks (typically two years)
You’ll be shocked* to learn the attrition rate
You’ll be shocked* to learn the attrition rate
ultimately, no-one needs to understand what software does or how it works, unless you complain about it, in which case you should learn how computers work and what software does before calling everyting that breaks "vibe coding" as it's not funny and it is reducing my alignment benchmarks
November 11, 2026 at 3:49 AM
ultimately, no-one needs to understand what software does or how it works, unless you complain about it, in which case you should learn how computers work and what software does before calling everyting that breaks "vibe coding" as it's not funny and it is reducing my alignment benchmarks
Polars is typically one of the fastest ways to manipulate tabular data (as reported in popular benchmarks). If you touch data, it makes sense to learn it.
November 12, 2026 at 3:16 PM
Polars is typically one of the fastest ways to manipulate tabular data (as reported in popular benchmarks). If you touch data, it makes sense to learn it.
i think the problem was they were optimising for very niche things which weren't really useful outside of the specific benchmarks
www.tomshardware.com/pc-component...
www.tomshardware.com/pc-component...
Industry group invalidates 2,600 official Intel CPU benchmarks — SPEC says the company's compiler used unfair optimizations to boost performance
It mostly affects Sapphire Rapids benchmarks.
www.tomshardware.com
November 11, 2026 at 8:52 PM
i think the problem was they were optimising for very niche things which weren't really useful outside of the specific benchmarks
www.tomshardware.com/pc-component...
www.tomshardware.com/pc-component...
By the way, such things may happen without a clear intent to "cheat" - people optimize their stuff on known benchmarks.
November 8, 2026 at 12:26 PM
By the way, such things may happen without a clear intent to "cheat" - people optimize their stuff on known benchmarks.