Prove the lift · AI model performance evaluation
gpt-4o vs llama-3.1-70b
+21-point lift for gpt-4o on ecommerce-catalog-norm
Test summary
This benchmark evaluates gpt-4o against llama-3.1-70b on the ecommerce-catalog-norm v1 dataset (5 rows), scored by an LLM-as-judge (llama-3.1-8b, run locally). gpt-4o reached a 66% pass rate versus 45% for llama-3.1-70b — a +21-point lift.
- Base model
- llama-3.1-70b
- via ollama · 45% pass rate
- Refined model
- gpt-4o
- via openai · 66% pass rate · 0.9s p95
Base pass rate
45%
Refined pass rate
66%
Refined p95
0.9s
Est. tokens saved
3.7K
+0pts
refined beats base on 5 rows
0%
Base model0%
Invoked-refined▲4 improved▼0 regressed●0 unchanged
Per-row results
1Classify a listing into the right category node0% → 100%+100
2Extract material + color from a product title0% → 100%+100
3Deduplicate two near-identical SKUs0% → 100%+100
4Normalize a free-text size into a standard enum0% → 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