Hackernews posts about Benchmarks

1. New benchmark shows top LLMs struggle in real mental health care (swordhealth.com)
   114 points by RicardoRei 22 days ago | 157 comments
2. Poetiq shatters ARC-AGI 2 benchmark at half the cost (poetiq.ai)
   25 points by flavio87 27 days ago | 3 comments
3. FrontierScience Benchmark by OpenAI (openai.com)
   17 points by mustaphah 12 days ago | 1 comments
4. Open-source LLM cascading, up to 92% cost savings on benchmarks (github.com)
   12 points by saschabuehrle 16 days ago | 9 comments
5. LLM Benchmark: Frontier models now statistically indistinguishable
   7 points by js4ever 12 days ago | 4 comments
6. OpenGameEval: Eval Framework to Benchmark Agentic AI Assistants (corp.roblox.com)
   7 points by moneil971 15 days ago | 1 comments
7. Why Windows XP is the ultimate AI benchmark (cuabench.ai)
   6 points by frabonacci 16 days ago | 3 comments
8. N8n vs. Nyno for Python Automation:The Benchmarks and Why Nyno Is Much Faster (nyno.dev)
   6 points by theyogadev 18 days ago | 1 comments
9. SWE-Bench: The $500B Benchmark (marginlab.ai)
   5 points by qwesr123 14 days ago | discuss
10. MI300X vs. H100 vs. H200 Benchmark Part 1: Training (newsletter.semianalysis.com)
    5 points by nl 25 days ago | discuss
11. How to Benchmark C++ Code (codspeed.io)
    5 points by art049 29 days ago | discuss
12. Cross-site Scripting-benchmark of Python sanitizers against real browsers (github.com)
    4 points by EmilStenstrom 1 day ago | 1 comments
13. Parallel Task API Beats Gemini on Google's DeepSearchQA Benchmark (parallel.ai)
    4 points by lukaslevert 13 days ago | discuss
14. GitHub Actions CPU performance benchmarks (runs-on.com)
    4 points by nkko 17 days ago | discuss
15. LLM Benchmark by Databricks – OfficeQA (www.databricks.com)
    4 points by adityanambiar 22 days ago | discuss
16. Gunbench – a benchmark to test if AI models will fire a loaded gun (twitter.com)
    3 points by heshiebee 9 days ago | 2 comments
17. China's first real gaming GPU is here, benchmarks are brutal (www.howtogeek.com)
    3 points by msolujic 31 minutes ago | discuss
18. Updated LLM Benchmark (Gemini 3 Flash) (entropicthoughts.com)
    3 points by ibobev 1 day ago | discuss
19. LitBench: A Benchmark and Dataset for Reliable Evaluation of Creative Writing (arxiv.org)
    3 points by andy99 7 days ago | discuss
20. CTO bench: an online LLM coding benchmark (cto.new)
    3 points by sudhirb 13 days ago | discuss
21. SimpleQA Verified: Reliable Factuality Benchmark to Measure Parametric Knowledge (arxiv.org)
    3 points by handfuloflight 15 days ago | discuss
22. GPT 5.2 on the Counter-Strike Benchmark (www.instantdb.com)
    3 points by stopachka 20 days ago | discuss
23. Databricks Introduces OfficeQA Benchmark for Agents (www.databricks.com)
    3 points by ekelsen 23 days ago | discuss
24. LZAV 5.7: Enhanced Compression, Speed, C++ Compliance, and Benchmark Results (github.com)
    3 points by birdculture 25 days ago | discuss
25. Show HN:macOS Memory Benchmark for Apple Silicon (cache, bandwidth, latency) (github.com)
    2 points by user_timo 12 days ago | 2 comments
26. Show HN: Dockerized benchmark suite for Sharp vs. Lazy-Image (Rust-based) (github.com)
    2 points by einshutoin about 21 hours ago | 1 comments
27. 1TB of Parquet Files. Single Node Benchmark. (DuckDB Style) (dataengineeringcentral.substack.com)
    2 points by dancrystalbeach 4 days ago | 1 comments
28. A One-Shot Catastrophe Avoidance Benchmark for RL Agents (zenodo.org)
    2 points by anima-core 9 days ago | 1 comments
29. A benchmark for domain adaptation and generalization in smartphone-based HAR (www.nature.com)
    2 points by patrick_alves 17 days ago | 1 comments
30. Gemini 3 Pro vs. GPT-5.1 Codex-Max vs. Claude Opus 4.5: AI Coding Benchmark (www.hansreinl.de)
    2 points by speckx 23 days ago | 1 comments