Prove the lift · AI model performance evaluation
claude-opus-4-6 vs claude-opus-4-8
+19-point lift for claude-opus-4-6 on ecommerce-catalog-norm
Test summary
This benchmark evaluates claude-opus-4-6 against claude-opus-4-8 on the ecommerce-catalog-norm v2 dataset (5 rows), scored by an LLM-as-judge (llama-3.1-8b). claude-opus-4-6 reached a 49% pass rate versus 30% for claude-opus-4-8 — a +19-point lift.
- Base model
- claude-opus-4-8
- via anthropic · 30% pass rate
- Refined model
- claude-opus-4-6
- via anthropic · 49% pass rate · 1.6s p95
Base pass rate
30%
Refined pass rate
49%
Refined p95
1.6s
Est. tokens saved
2.8K
+0pts
refined beats base on 5 rows
0%
Base model0%
Invoked-refined▲0 improved▼0 regressed●4 unchanged
Per-row results
1Normalize a free-text size into a standard enum0% → 0%0
2Classify a listing into the right category node100% → 100%0
3Deduplicate two near-identical SKUs100% → 100%0
4Extract material + color from a product title100% → 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 InvokedGenerated with Invoked · Browse all benchmarks