Prove the lift · AI model performance evaluation
gpt-5 vs gpt-5.1
+3-point lift for gpt-5 on ecommerce-catalog-norm
Test summary
This benchmark evaluates gpt-5 against gpt-5.1 on the ecommerce-catalog-norm v2 dataset (5 rows), scored by an LLM-as-judge (llama-3.1-8b). gpt-5 reached a 38% pass rate versus 35% for gpt-5.1 — a +3-point lift.
- Base model
- gpt-5.1
- via openai · 35% pass rate
- Refined model
- gpt-5
- via openai · 38% pass rate · 1.1s p95
Base pass rate
35%
Refined pass rate
38%
Refined p95
1.1s
Est. tokens saved
6.6K
+0pts
refined beats base on 5 rows
0%
Base model0%
Invoked-refined▲1 improved▼0 regressed●3 unchanged
Per-row results
1Deduplicate two near-identical SKUs100% → 100%0
2Normalize a free-text size into a standard enum0% → 0%0
3Extract material + color from a product title100% → 100%0
4Classify a listing into the right category node0% → 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