Hackernews posts about Benchmarks

1. Tau² benchmark: How a prompt rewrite boosted GPT-5-mini by 22% (quesma.com)
   197 points by blndrt 16 days ago | 65 comments
2. Evals in 2025: going beyond simple benchmarks to build models people can use (github.com)
   80 points by jxmorris12 15 days ago | 8 comments
3. When hackathon judging is a public benchmark: my report from Hack the North (github.com)
   18 points by frabonacci 6 days ago | 3 comments
4. Why most AI coding benchmarks are misleading (COMPASS paper) (arxiv.org)
   13 points by jmeaden 14 days ago | 2 comments
5. Linux 6.17 File-System Benchmarks, Including OpenZFS and Bcachefs (www.phoronix.com)
   11 points by Bogdanp 13 days ago | 2 comments
6. GamerNexus to benchmarks GPUs on Linux [video] (www.youtube.com)
   11 points by ekianjo 6 days ago | 1 comments
7. Network and Storage Benchmarks for LLM Training on the Cloud (maknee.github.io)
   10 points by Bogdanp 21 days ago | discuss
8. Show HN: LLM Creative Story‑Writing Benchmark V3 (github.com)
   8 points by zone411 23 days ago | discuss
9. Qualcomm's 18-core Snapdragon X2 Elite Extreme dominates in first benchmarks (www.tomshardware.com)
   7 points by rbanffy 3 days ago | discuss
10. RVV benchmark Tenstorrent Ascalon X (camel-cdr.github.io)
    7 points by fidotron 7 days ago | discuss
11. Qualcomm's 18-core Snapdragon X2 Elite Extreme dominates in first benchmarks (www.tomshardware.com)
    6 points by rbanffy 3 days ago | 2 comments
12. The Illusion of Readiness: Stress Testing Frontier Models on Medical Benchmarks (arxiv.org)
    6 points by mellosouls 7 days ago | discuss
13. Show HN: LLM Round‑Trip Translation Benchmark (github.com)
    6 points by zone411 17 days ago | discuss
14. Open source benchmark for running AI models on consumer GPUs/CPUs (allaboutdata.substack.com)
    5 points by albedan 22 days ago | discuss
15. Retrieval Embedding Benchmark (mteb-leaderboard.hf.space)
    4 points by fzliu about 2 hours ago | discuss
16. ROMA: Meta-agents with task decomposition, backed by benchmark wins (github.com)
    4 points by mustaphah 18 days ago | discuss
17. Intel Arc Pro B50 Linux Performance Benchmarks (www.phoronix.com)
    4 points by high_na_euv 29 days ago | discuss
18. Retrieval Embedding Benchmark (RTEB) (huggingface.co)
    3 points by fzliu 4 days ago | 1 comments
19. Raspberry Pi 500 Benchmarks: Mechanical Keyboard Computer, 16GB RAM and NVMe SSD (www.phoronix.com)
    3 points by Alupis 6 days ago | 1 comments
20. GitHub Actions CPU performance benchmarks (runs-on.com)
    3 points by anner_ 9 days ago | 1 comments
21. AI Spreadsheet Benchmark [pdf] (huggingface.co)
    3 points by patife 10 days ago | 1 comments
22. Code Review Benchmark (blog.macroscope.com)
    3 points by TheAnkurTyagi 4 days ago | discuss
23. What are popular AI coding benchmarks measuring? (blog.nilenso.com)
    3 points by birdculture 5 days ago | discuss
24. What are popular AI coding benchmarks measuring? (blog.nilenso.com)
    3 points by todsacerdoti 8 days ago | discuss
25. Why behavior beats device and network in bot detection (benchmarks inside) (research.roundtable.ai)
    3 points by timshell 10 days ago | discuss
26. Terminal-bench: a benchmark for AI agents in terminal environments (www.tbench.ai)
    3 points by cpard 19 days ago | discuss
27. LLM-optimizer: Benchmark and optimize LLM inference across frameworks with ease (github.com)
    3 points by djhu9 21 days ago | discuss
28. SimpleQA Verified: Reliable Factuality Benchmark to Measure Parametric Knowledge (arxiv.org)
    3 points by simonpure 22 days ago | discuss
29. Claude Code 2.0 Router – Aligning LLM routing to preferences, not benchmarks (github.com)
    2 points by honorable_coder 2 days ago | 1 comments
30. Benchmark for Local LLMs with German "Who Wants to Be a Millionaire" Questions (github.com)
    2 points by thunderbong 30 days ago | 1 comments