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 model0%
Invoked-refined▲1 improved▼0 regressed●3 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 InvokedGenerated with Invoked · Browse all benchmarks