Hackernews posts about Benchmarks

RSS feed for Benchmarks

181
newBtrfs/ZFS/bcachefs under workloads classic benchmarks skipbartosz.fenski.pl
▲ 179farlight 15d 💬 190
182
newRTK reports token savings, but our cost benchmarks disagreequesma.com
▲ 170michalwarda 23d 💬 84
183
newShow HN: JevBench, a reproducible benchmark for typed decision modelsbenchmarkheaven.com
▲ 154florianstandhar 12d 💬 39
184
newRecreating Minecraft Is Not a Benchmarkkuber.studio
▲ 73kuberwastaken 28d 💬 74
185
newBad benchmarks and evals: Senior SWE-Bench, napkin math, and winter tiresdanluu.com
▲ 56luu 23d 💬 46
186
newBenchmark: CadQuery vs. OpenSCAD for agentic CAD workmodelrift.com
▲ 40jetter 22d 💬 65
187
newUncensored and Offensive Security AI Models Benchmarkgithub.com
▲ 38soltanov 6d 💬 12
188
new1Password's AI patching benchmark is misleadingblog.trailofbits.com
▲ 37darkamaul 19d 💬 9
189
newAgents on Rails: Best model solves 35% of feature benchmark runsrubyonrails.org
▲ 20chalmovsky 23d 💬 4
190
newDoGBench: The first user-facing docs generation benchmark. No model scores >50%dogbench.ai
▲ 18prithvi2206 3d 💬 3
191
newAuto-autoresearch: self-improving agents on Karpathy's NanoChat benchmarkrekursiv.ai
▲ 13hyperparticle 19d 💬 5
192
newThe case to BYOB: build your own (coding) benchmarksbyobench.ai
▲ 11oaa36 24d 💬 2
193
newThe Two MMLU Scores: What a Benchmark Name Does Not Fixzatona.dev
▲ 8gmays 21d 💬 3
194
newInsurance Agent Benchmark: 166 real-world cases for evaluating insurance AIwww.askcooper.ai
▲ 7jsc39 17d discuss
195
newKernelBench: Can LLMs Write GPU Kernels? – Benchmark and Toolkit, Torch –> CUDAgithub.com
▲ 6peter_d_sherman 3d discuss
196
newWhy Bend 2's typechecker benchmarks are misleading (and its practical flaws)gist.github.com
▲ 6Nezk 16d discuss
197
newShow HN: Benchmark: AI doesn't find bugs unless you tell it what's wrongswesweep.com
▲ 5lieret 3d 💬 2
198
newiOS and macOS CI benchmark: Avrea is 3-23x faster than GitHub Actionsavrea.com
▲ 5leolannenmaki 4d 💬 2
199
newShow HN: Livenerf – a benchmark for whether Opus 5.5 gets nerfedgithub.com
▲ 5ninjahawk1 12d 💬 2
200
newShow HN: Compute:Arena – Community submitted local AI benchmarkscomputearena.ai
▲ 5prabod 18d 💬 2
201
newAsk HN: Model sycophancy benchmarks?
▲ 5gradus_ad 28d 💬 2
202
newShow HN: A benchmark comparison of C++ vs. Node.js performancevikky2810.github.io
▲ 5vikky2810 10d 💬 1
203
newBecoming a Benchmarkterrytao.wordpress.com
▲ 5bluepeter 17d discuss
204
newBenchmarks are more broken than we could have imaginedwww.horizonanalyticslabs.com
▲ 4chillacy 12d 💬 1
205
newThe Cure for Cancer Is Not a Pure Math Benchmarkscholars-stage.org
▲ 4zdw 15d 💬 1
206
newMoorcheh Edge on Arduino UNO Q vs. Ventuno Q: 1536-D Vector Benchmarkmoorcheh.ai
▲ 4supportm 2d discuss
207
newgo/codegolf benchmark: frontier models vs. Google's 2015 code golfersbjin.github.io
▲ 4bjin 6d discuss
208
newM5 Ultra first benchmarks – Geekbenchbrowser.geekbench.com
▲ 4happyopossum 19d discuss
209
newThe Benchmark Creator Is Almost Always on the Podiumpymupdf.io
▲ 4akaybk 19d discuss
210
newLLM Benchmark for de-identification and synthesishuggingface.co
▲ 3akamor 11d 💬 2