Prove the lift · AI model performance evaluation

llama-4-maverick vs o3-mini

+23-point lift for llama-4-maverick on ecommerce-catalog-norm

Test summary

This benchmark evaluates llama-4-maverick against o3-mini on the ecommerce-catalog-norm v3 dataset (5 rows), scored by an LLM-as-judge (claude-haiku-4-5). llama-4-maverick reached a 76% pass rate versus 53% for o3-mini — a +23-point lift.

Base model
o3-mini
via openai · 53% pass rate
Refined model
llama-4-maverick
via meta · 76% pass rate · 0.6s p95
Base pass rate
53%
Refined pass rate
76%
Refined p95
0.6s
Est. tokens saved
2.4K
+0pts
refined beats base on 5 rows
0%
Base model
0%
Invoked-refined
1 improved0 regressed3 unchanged

Per-row results

1Normalize a free-text size into a standard enum100%100%0
2Classify a listing into the right category node100%100%0
3Deduplicate two near-identical SKUs100%100%0
4Extract material + color from a product title0%100%+100
Prove the lift on your own data.

Run any two models over your tasks, judged automatically, and see the improvement — in seconds.

Try Invoked
Generated with Invoked · Browse all benchmarks