Prove the lift · AI model performance evaluation

gpt-4-turbo vs mistral-large

+21-point lift for gpt-4-turbo on insurance-extraction-eval

Test summary

This benchmark evaluates gpt-4-turbo against mistral-large on the insurance-extraction-eval v3 dataset (5 rows), scored by an LLM-as-judge (gpt-4o-mini). gpt-4-turbo reached a 68% pass rate versus 47% for mistral-large — a +21-point lift.

Base model
mistral-large
via mistral · 47% pass rate
Refined model
gpt-4-turbo
via openai · 68% pass rate · 0.9s p95
Base pass rate
47%
Refined pass rate
68%
Refined p95
0.9s
Est. tokens saved
1.3K
+0pts
refined beats base on 5 rows
0%
Base model
0%
Invoked-refined
▲2 improved▼0 regressed●3 unchanged

Per-row results

1Named-peril coverage determination under a basic HO form0% → 0%0
2Suit-limitation clause: is a late-filed claim contractually barred?0% → 100%+100
3Business-interruption period-of-restoration calculation0% → 100%+100
4Coinsurance 80% clause recovery on an under-insured building100% → 100%0
5Aggregate deductible across a loss sequence under a per-occurrence + annual cap100% → 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 Invoked
Generated with Invoked · Browse all benchmarks