Prove the lift · AI model performance evaluation
llama-3.3-70b vs mixtral-8x7b
+16-point lift for llama-3.3-70b on ecommerce-catalog-norm
Test summary
This benchmark evaluates llama-3.3-70b against mixtral-8x7b on the ecommerce-catalog-norm v3 dataset (5 rows), scored by an LLM-as-judge (llama-3.1-8b). llama-3.3-70b reached a 52% pass rate versus 36% for mixtral-8x7b — a +16-point lift.
- Base model
- mixtral-8x7b
- via mistral · 36% pass rate
- Refined model
- llama-3.3-70b
- via meta · 52% pass rate · 3.1s p95
Base pass rate
36%
Refined pass rate
52%
Refined p95
3.1s
Est. tokens saved
2.9K
+0pts
refined beats base on 5 rows
0%
Base model0%
Invoked-refined▲1 improved▼0 regressed●3 unchanged
Per-row results
1Classify a listing into the right category node100% → 100%0
2Extract material + color from a product title100% → 100%0
3Deduplicate two near-identical SKUs0% → 100%+100
4Normalize a free-text size into a standard enum0% → 0%0
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