Prove the lift · AI model performance evaluation
gpt-4o-mini vs claude-haiku-4-5
+19-point lift for gpt-4o-mini on ecommerce-catalog-norm
Test summary
This benchmark evaluates gpt-4o-mini against claude-haiku-4-5 on the ecommerce-catalog-norm v1 dataset (5 rows), scored by an LLM-as-judge (llama-3.1-8b). gpt-4o-mini reached a 47% pass rate versus 28% for claude-haiku-4-5 — a +19-point lift.
- Base model
- claude-haiku-4-5
- via anthropic · 28% pass rate
- Refined model
- gpt-4o-mini
- via openai · 47% pass rate · 1.9s p95
Base pass rate
28%
Refined pass rate
47%
Refined p95
1.9s
Est. tokens saved
11.4K
+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 enum0% → 0%0
2Deduplicate two near-identical SKUs100% → 100%0
3Classify a listing into the right category node0% → 0%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