Benchmark
git_log_format
12 fixtures

Models ranked by pass rate on git_log_format. A model that dominates overall might rank lower here. That's the point.

Loading...

Quality and efficiency for git_log_format only.

Loading...

API cost summed from fixture results in this benchmark.

Loading...

API latency from calls made for fixtures in this benchmark.

Loading...

Source token counts come from provider-reported usage; GitBench calculates the displayed aggregates from them. Provider tokenizers and accounting methods may differ. Learn more ->

Loading...
Loading...