Hackernews posts about Benchmarks

1. GLM 5.2 beats Claude in our benchmarks (semgrep.dev)
   1113 points by jms703 22 days ago | 516 comments
2. Kimi K3, and what we can still learn from the pelican benchmark (simonwillison.net)
   404 points by droidjj 3 days ago | 222 comments
3. Senior SWE-Bench: open-source benchmark that assesses agents as senior engineers (senior-swe-bench.snorkel.ai)
   186 points by matt_d 19 days ago | 120 comments
4. German AI consortium releases Soofi S, an open 30B model that tops benchmarks (the-decoder.com)
   146 points by amai 4 days ago | 34 comments
5. Lies, Damn Lies and Database Benchmarks (questdb.com)
   58 points by eigenBasis 28 days ago | 28 comments
6. Claude Sonnet 5 – benchmark results (artificialanalysis.ai)
   41 points by lucamark 20 days ago | 17 comments
7. PostgreSQL Benchmark: AWS RDS vs. Self-Hosted on Hetzner (2026) (hostim.dev)
   28 points by pv1337 14 days ago | 13 comments
8. Agentic test processes, LLM benchmarks, and other notes on agentic coding fr (danluu.com)
   20 points by lifeisstillgood 12 days ago | 2 comments
9. FrontierFinance: The largest open benchmark for investor workflows (research.samaya.ai)
   18 points by ashwinpp 11 days ago | 2 comments
10. Show HN: Trying to fix the web scraping industry's benchmark problem (github.com)
    18 points by rohitshenoy 4 days ago | discuss
11. Show HN: Benchmark your eng team's AI agent maturity in 5 minutes (agent-benchmarks.com)
    14 points by adamgold7 7 days ago | 8 comments
12. Benchmarks Are Dead (For Us) (poetiq.ai)
    11 points by oliversisson 5 days ago | 1 comments
13. AI agents write Ruby but can't navigate it: a 5-model, 13-codebase benchmark (github.com)
    9 points by luuuc 7 days ago | 2 comments
14. Benchmark object storage in objects/s, not GB/s (fractalbits.com)
    8 points by zzsheng 27 days ago | discuss
15. Ask HN: Are there good security benchmarks for LLMs?
    7 points by melvinroest 15 days ago | 1 comments
16. Perfectly Hitting the Wrong Target: The Story of an AI Code Review Benchmark (shrsv.hexmos.com)
    6 points by atomicnature 8 days ago | 1 comments
17. About Latency-focused disk benchmarks for Linux VPS environments (github.com)
    6 points by ashitlerferad 22 days ago | 1 comments
18. Ollama vs. Llama.cpp – Quick Benchmark (blawg.pages.dev)
    6 points by caveman23 9 days ago | discuss
19. Show HN: SOCBench – an open benchmark for AI on SoC tasks (github.com)
    6 points by krmayankb 13 days ago | discuss
20. Every AI Memory Benchmark Has an Asterisk (tenureai.dev)
    6 points by freewilly25 26 days ago | discuss
21. DOJ Requires Egg Producers to End Coordinated Benchmark Manipulation (www.justice.gov)
    5 points by gnabgib 20 days ago | 1 comments
22. Political Neutrality Benchmark of popular AI models (neutralityproject.org)
    5 points by ryzvonusef 9 days ago | discuss
23. How can Rust be so fast in the TechEmpower Web Framework Benchmarks? (kerkour.com)
    5 points by Keyb0ardWarri0r 14 days ago | discuss
24. A benchmark revealing an average memory-retrieval accuracy of 9% (zendoric.com)
    5 points by jflynt76 16 days ago | discuss
25. GPT-5.5-Cyber Tops Mythos 5 on Cybersecurity Benchmark (twitter.com)
    5 points by delichon 28 days ago | discuss
26. Show HN: Is grep enough? A transparent benchmark for agentic code navigation (entelligentsia.github.io)
    4 points by bonigv 21 days ago | 2 comments
27. Show HN: TreasuryBench – an open benchmark for personal-finance AI advice (github.com)
    4 points by juneadkhan 25 days ago | 1 comments
28. GPT-5.6 Luna Showed a Better ROI on Cybersecurity Benchmark (semgrep.dev)
    4 points by j12y 7 days ago | discuss
29. PrivacyBench: An open benchmark for de-identifying text that scores synthesis (huggingface.co)
    4 points by joewferrara 7 days ago | discuss
30. General LLMs outperform specialized clinical AI tools on medical benchmarks (www.nature.com)
    4 points by sebg 25 days ago | discuss