MaxxBench – "Nice DeepSWE score. But is it true?"

(maxxbench.unlap.ai)

29 points | by antiuniverse 1 hour ago

3 comments

  • Neywiny 20 minutes ago
    This is perfect. Real programming has a ton of these instances of minor changes.
  • saejox 11 minutes ago
    There is always a huge discrepancy between benchmarks and real world capabilities.

    For my use case deepseek 4.1 flash is almost as dumb as haiku 5.5. Both are fast garbage producers.

    • embedding-shape 1 minute ago
      [delayed]
    • jeffbee 6 minutes ago
      I was beginning to worry I had overlooked the inner beauty of DeepSeek. When I have tried it, it was totally useless. Never understood HN cheering for it.
  • brcmthrowaway 22 minutes ago
    Two brothers created a benchmark, family is so proud.