Hackernews posts about Benchmarks

1. Benchmark Framework Desktop Mainboard and 4-node cluster (github.com)
   203 points by geerlingguy 11 days ago | 88 comments
2. Launch HN: Design Arena (YC S25) – Head-to-head AI benchmark for aesthetics
   72 points by grace77 6 days ago | 24 comments
3. Show HN: Evaluating LLMs on creative writing via reader usage, not benchmarks (www.narrator.sh)
   36 points by Jetwu 4 days ago | 12 comments
4. GPT-5 doubles performance in offensive security benchmark (xbow.com)
   25 points by summarity 1 day ago | 3 comments
5. Final Benchmarks of Clear Linux on Intel: ~48% Faster Than Ubuntu Out-of-the-Box (www.phoronix.com)
   23 points by mfiguiere 24 days ago | 6 comments
6. Benchmarks in CI: Escaping the Cloud Chaos (codspeed.io)
   21 points by adriencaccia 18 days ago | 6 comments
7. Qwen3 235B beats Claude on some code benchmarks (huggingface.co)
   21 points by willahmad 28 days ago | 2 comments
8. The AGI Final Frontier: The CLJ-AGI Benchmark (raspasov.posthaven.com)
   19 points by raspasov 30 days ago | 16 comments
9. Show HN: Predict GPT-5 skills with a community AI benchmark
   13 points by andrewxhill 16 days ago | 2 comments
10. Show HN: A benchmark + latency sim for LLM db queries: ClickHouse / Postgres (github.com)
    12 points by oatsandsugar 13 days ago | 3 comments
11. AI Startup Caught Cheating on Benchmark Papers (twitter.com)
    10 points by elasxies 6 days ago | 1 comments
12. Framework Desktop Hands On: First Impressions (Benchmarks, Gaming, AI Models) (boilingsteam.com)
    10 points by ekianjo 11 days ago | 1 comments
13. The Brokk Power Ranking LLM Coding Benchmark (brokk.ai)
    10 points by jbellis 6 days ago | discuss
14. TaxCalcBench: A benchmark for evaluating AI's ability to calculate tax returns (www.columntax.com)
    10 points by sundaypancakes 26 days ago | discuss
15. OpenAI's GPT-OSS models benchmarks worse than DeepSeek R1 and Qwen3 235B (xcancel.com)
    8 points by pu_pe 12 days ago | 1 comments
16. Show HN: Bazaar – a new LLM benchmark for economic reasoning under uncertainty (github.com)
    8 points by zone411 27 days ago | 1 comments
17. Show HN: Llm-benchmark – Benchmarks LLM-optimized code across multiple providers (github.com)
    8 points by thomasfromcdnjs 30 days ago | 1 comments
18. Cheating on Quantum Computing Benchmarks (www.schneier.com)
    5 points by decimalenough 18 days ago | 1 comments
19. AMD Threadripper 9980X and 9970X Linux Benchmarks (www.phoronix.com)
    5 points by Bezod 19 days ago | 1 comments
20. Giving Benchmarks a Boat (buttondown.com)
    5 points by eatonphil 21 days ago | 1 comments
21. GPT-5 Is Good, Actually: The Agony and Ecstasy of Public Benchmarks (hackbot.dad)
    5 points by dixie_flatline 1 day ago | discuss
22. Learning OLAP by writing a ClickHouse vs. Postgres benchmark (github.com)
    5 points by oatsandsugar 10 days ago | discuss
23. Show HN: Fast360 – A web tool to benchmark open-source OCR models side-by-side (fast360.xyz)
    4 points by yanaimngvov about 19 hours ago | 1 comments
24. OpenAI has once again set a new VC benchmark
    4 points by oxsatsuma 21 days ago | discuss
25. Spiral-Bench: A new benchmark measuring LLM sycophancy and delusion (eqbench.com)
    3 points by joaompinto about 17 hours ago | 1 comments
26. NextCoder by Microsoft — LLM performing on par with GPT-4o on complex benchmarks (huggingface.co)
    3 points by maxloh 10 days ago | discuss
27. Is your AI benchmark lying to you? (www.nature.com)
    3 points by mdp2021 13 days ago | discuss
28. Prisma ORM Without Rust: Latest Performance Benchmarks (www.prisma.io)
    3 points by bodash 14 days ago | discuss
29. PostgreSQL JavaScript client benchmark – pgline vs. pg vs. Bun.sql vs. Postgres (github.com)
    3 points by theThree 17 days ago | discuss
30. Benchmarks in CI: Escaping the Cloud Chaos (codspeed.io)
    3 points by art049 19 days ago | discuss