Hackernews posts about Benchmarks
- Claude Code daily benchmarks for degradation tracking (marginlab.ai)
- A real-world benchmark for AI code review (www.qodo.ai)
- Show HN: BioTradingArena – Benchmark for LLMs to predict biotech stock movements (www.biotradingarena.com)
- Database Benchmarks Lie (If You Let Them) (www.exasol.com)
- Browser Agent Benchmark: Comparing LLM models for web automation (browser-use.com)
- New SpacemiT K3 RISC-V Chip Beats Raspberry Pi 5 in Early Benchmarks (www.cnx-software.com)
- The hunt for Benchmark Modula-2 (2018) (amigasourcepres.gitlab.io)
- Show HN: Open Benchmarks Grants– a $3M commitment to close the AI eval gap (benchmarks.snorkel.ai)
- I built a tool to benchmark my AI agent's API costs (local001.com)
- GLM-5 topped the coding benchmarks. Then I used it (charlesazam.com)
- What those AI benchmark numbers mean (ngrok.com)
- China's Loongson 3B6000 Benchmarks (www.phoronix.com)
- Realworld benchmark between Codex 5.3 and Opus 4.6 (swe-agi.com)
- Updated LLM Benchmark (Gemini 3 Flash) (entropicthoughts.com)
- LLM Compare – side-by-side benchmark viewer for 250 models (static, no back end) (broskees.github.io)
- Valkey is now outperforming Redis in benchmarks: 37% higher write throughput (andrewbaker.ninja)
- Are AI agents ready for the workplace? A new benchmark raises doubts (techcrunch.com)
- The Emerging Science of ML Benchmarks (mlbenchmarks.org)
- Show HN: Jsbenchmarks.com – Real-world JavaScript framework benchmarks (jsbenchmarks.com)
