Hackernews posts about HumanEval

  1. Maincoder-1B – an open 1B-parameter coding model with 76% HumanEval (huggingface.co)
    4 points by MainNews 9 months ago | 3 comments
  2. Show HN: S0 Tuning – +23.6pp on HumanEval by tuning state, not weights (github.com)
    2 points by jacknotold 6 months ago | 2 comments
  3. Show HN: Aflow achieves 96.2% on HumanEval at 4.55% of GPT-4's cost (twitter.com)
    1 points by metagpt almost 2 years ago | discuss
  4. Launch HN: Strata (YC P25) – One MCP server for AI to handle thousands of tools
    133 points by wirehack 12 months ago | 66 comments
  5. LLM Benchmark: Frontier models now statistically indistinguishable
    7 points by js4ever 9 months ago | 4 comments
  6. Show HN: I built the LLM Comparison Tool I wish existed (llm-stats.com)
    7 points by JonathanChavez over 1 year ago | 3 comments
  7. Show HN: Benchmark AI on your actual code (GPT-5, Claude, Grok, Gemini, o3) (codelens.ai)
    7 points by codelensai 11 months ago | discuss
  8. Show HN: European Swallow AI – Sonnet-quality coding at $2.60/M tokens (www.europeanswallowai.com)
    7 points by joaquim_d 11 months ago | discuss
  9. Diffusion LLM may make most of the AI engineering stack obsolete
    3 points by victorpiles99 6 months ago | discuss
  10. Show HN: Loki Mode hit 99.67% SWE-Bench – MAF built a SaaS overnight (github.com)
    2 points by slogansand 8 months ago | 5 comments
  11. Q Evaluation Harness: open-source evals for LLMs on q/kdb+ (github.com)
    2 points by erfan_mhi about 1 year ago | discuss
  12. Show HN: AIBenchy – Independent AI Leaderboard (aibenchy.com)
    1 points by XCSme 7 months ago | 1 comments
  13. ARCHE3-7B – Sparse Moe with SmartRouter and Foundation Curriculum Training
    1 points by OpenSynapseLabs 6 months ago | discuss
  14. Show HN: Kore – Stack based language where compiler is the reward function (github.com)
    1 points by processorx 7 months ago | discuss
  15. Show HN: Atlas: Independent Evals and Benchmarking for Generative AI Models (app.layerlens.ai)
    1 points by Arch223 over 1 year ago | discuss
  16. GPT5 is the best coding LLM because other LLMs admit it?
    1 points by adinhitlore about 1 year ago | 8 comments