Prove the lift · AI model performance evaluation

gpt-4o vs o3-mini

+2-point lift for gpt-4o on ecommerce-catalog-norm

Test summary

This benchmark evaluates gpt-4o against o3-mini on the ecommerce-catalog-norm v2 dataset (5 rows), scored by an LLM-as-judge (gpt-4o-mini, run locally). gpt-4o reached a 49% pass rate versus 47% for o3-mini — a +2-point lift.

Base model
o3-mini
via openai · 47% pass rate
Refined model
gpt-4o
via openai · 49% pass rate · 1.3s p95
Base pass rate
47%
Refined pass rate
49%
Refined p95
1.3s
Est. tokens saved
5.8K
+0pts
refined beats base on 5 rows
0%
Base model
0%
Invoked-refined
1 improved0 regressed3 unchanged

Per-row results

1Classify a listing into the right category node0%100%+100
2Deduplicate two near-identical SKUs100%100%0
3Extract material + color from a product title100%100%0
4Normalize a free-text size into a standard enum100%100%0
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