Compare Benchmark Runs

Put individual benchmark runs side by side — specific model, tool and hardware. The best value in each row is highlighted. Share the URL to share this comparison.

Add runs to compare from the Benchmarks page — tick the runs you want and hit “Compare”.

cmvgtb2gcmt13n1d

No data found for the current selection.

KAT-Coder-V2.5-Dev-OptiQ-4bit on Apple M4 Max vs KAT-Coder-V2.5-Dev-OptiQ-4bit on Apple M4 Max — local LLM run comparison | llm-bench.io