Powered by CrucibleForge
Documentation
How the benchmark works, how to run the same tests on your own models, and how the suite has changed.
How the scale grows
Every model takes the same standard test, and a perfect run scores 10 in each category. A model that scores at least 90% on a part unlocks a harder bonus pack for it, which adds points on top, so there is no ceiling. When the top models start clearing a pack, we add a harder one. That keeps one shared test for every model, from a small local model to a frontier API, and nobody tops out.
Why MakoBench?
The shortfin mako is commonly described as the fastest shark in the ocean: Wikipedia gives burst speeds of up to about 74 km/h, though estimates vary and such figures are hard to measure. We built the suite to run quickly, and the open-source engine CrucibleForge does the work underneath.
Run CrucibleForge on Your Own Models: Install Guide
Install CrucibleForge, the open-source engine behind MakoBench, point it at any OpenAI-compatible model and get Code and Chat scores, 10 each for a perfect standard run. Real commands, real output, and a 1.6-minute smoke test that cost 2 cents.
How MakoBench Works: Open LLM Benchmark Explained
MakoBench is our public LLM benchmark board: 29 models, one Total (Code plus Chat), an error margin on every score. The engine underneath is CrucibleForge, free and open source. Here is what it tests, how it judges, and what the board cannot tell you.
What MakoBench Tests, and What It Doesn't
MakoBench tests text models on two jobs, working code and role-play or companion chat. Here is which models belong on the board, which never will, and what a row needs before it gets a rank.
MakoBench Suite History: Earlier Versions
The MakoBench tests change from time to time, and a score only means something inside the suite that produced it. Here is where the earlier boards live and why we kept them.
Open Main Bench The numbers behind every page here.