AI article
I Sell Memory APIs. I'm Also Building the Benchmark. Here's How I'm Trying Not to Rig It.
Community description: Hey everyone. This time I'll go through what got me started on this benchmark, and the core of how...
Dev.to | Sep 13, 2026 | woochan
Automated excerpt
Our numbers are verified the same way as everyone else's. An empty answer scores full marks, anything invented scores zero. Both directions matter because they break differently. Each question scores between -1 and +1, and the results are averaged rather than summed. Nothing has been scored yet, and I'm not quoting numbers before there are numbers.
Selected automatically from source text; not independently written or fact-checked. Read the original for full context.