Prove the lift · AI model performance evaluation

gpt-4-turbo vs gpt-4o-mini

+15-point lift for gpt-4-turbo on legal-research-qa

Test summary

This benchmark evaluates gpt-4-turbo against gpt-4o-mini on the legal-research-qa v1 dataset (5 rows), scored by an LLM-as-judge (gpt-4o-mini). gpt-4-turbo reached a 59% pass rate versus 44% for gpt-4o-mini — a +15-point lift.

Base model
gpt-4o-mini
via openai · 44% pass rate
Refined model
gpt-4-turbo
via openai · 59% pass rate · 1.7s p95
Base pass rate
44%
Refined pass rate
59%
Refined p95
1.7s
Est. tokens saved
6.8K
+0pts
refined beats base on 5 rows
0%
Base model
0%
Invoked-refined
▲3 improved▼0 regressed●1 unchanged

Per-row results

1Extract the standard of review applied0% → 100%+100
2Determine whether a precedent was overruled100% → 100%0
3Identify the controlling statute in a fact pattern0% → 100%+100
4Summarize the holding of a cited appellate case0% → 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