Prove the lift · AI model performance evaluation

claude-opus-4-6 vs gpt-4o-mini

+23-point lift for claude-opus-4-6 on insurance-extraction-eval

Test summary

This benchmark evaluates claude-opus-4-6 against gpt-4o-mini on the insurance-extraction-eval v3 dataset (5 rows), scored by an LLM-as-judge (claude-haiku-4-5, run locally). claude-opus-4-6 reached a 50% pass rate versus 27% for gpt-4o-mini — a +23-point lift.

Base model
gpt-4o-mini
via openai · 27% pass rate
Refined model
claude-opus-4-6
via anthropic · 50% pass rate · 0.5s p95
Base pass rate
27%
Refined pass rate
50%
Refined p95
0.5s
Est. tokens saved
9.6K
+0pts
refined beats base on 5 rows
0%
Base model
0%
Invoked-refined
▲4 improved▼1 regressed●0 unchanged

Per-row results

1Suit-limitation clause: is a late-filed claim contractually barred?0% → 100%+100
2Named-peril coverage determination under a basic HO form0% → 100%+100
3Coinsurance 80% clause recovery on an under-insured building100% → 0%-100
4Pro-rata distribution across layered carriers on a covered loss0% → 100%+100
5Replacement cost vs ACV on a depreciated roof0% → 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 Invoked
Generated with Invoked · Browse all benchmarks