Prove the lift · AI model performance evaluation

claude-opus-4-8 vs mixtral-8x7b

+23-point lift for claude-opus-4-8 on insurance-extraction-eval

Test summary

This benchmark evaluates claude-opus-4-8 against mixtral-8x7b on the insurance-extraction-eval v3 dataset (7 rows), scored by an LLM-as-judge (claude-haiku-4-5). claude-opus-4-8 reached a 79% pass rate versus 56% for mixtral-8x7b — a +23-point lift.

Base model
mixtral-8x7b
via mistral · 56% pass rate
Refined model
claude-opus-4-8
via anthropic · 79% pass rate · 1.3s p95
Base pass rate
56%
Refined pass rate
79%
Refined p95
1.3s
Est. tokens saved
13.8K
+0pts
refined beats base on 7 rows
0%
Base model
0%
Invoked-refined
▲4 improved▼0 regressed●3 unchanged

Per-row results

1Subrogation waiver interaction with additional-insured status100% → 100%0
2Coinsurance 80% clause recovery on an under-insured building100% → 100%0
3Business-interruption period-of-restoration calculation0% → 100%+100
4Named-peril coverage determination under a basic HO form0% → 0%0
5Replacement cost vs ACV on a depreciated roof0% → 100%+100
6Pro-rata distribution across layered carriers on a covered loss0% → 100%+100
7Aggregate deductible across a loss sequence under a per-occurrence + annual cap0% → 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