Prove the lift · AI model performance evaluation

mistral-large vs claude-sonnet-4-6

+19-point lift for mistral-large on ecommerce-catalog-norm

Test summary

This benchmark evaluates mistral-large against claude-sonnet-4-6 on the ecommerce-catalog-norm v2 dataset (5 rows), scored by an LLM-as-judge (llama-3.1-8b). mistral-large reached a 43% pass rate versus 24% for claude-sonnet-4-6 — a +19-point lift.

Base model
claude-sonnet-4-6
via anthropic · 24% pass rate
Refined model
mistral-large
via mistral · 43% pass rate · 2.8s p95
Base pass rate
24%
Refined pass rate
43%
Refined p95
2.8s
Est. tokens saved
2.9K
+0pts
refined beats base on 5 rows
0%
Base model
0%
Invoked-refined
▲1 improved▼1 regressed●2 unchanged

Per-row results

1Classify a listing into the right category node100% → 0%-100
2Extract material + color from a product title0% → 100%+100
3Deduplicate two near-identical SKUs0% → 0%0
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 Invoked
Generated with Invoked · Browse all benchmarks