Prove the lift · AI model performance evaluation

gemini-1.5-pro vs gemini-1.5-flash

+18-point lift for gemini-1.5-pro on support-ticket-triage

Test summary

This benchmark evaluates gemini-1.5-pro against gemini-1.5-flash on the support-ticket-triage v2 dataset (6 rows), scored by an LLM-as-judge (llama-3.1-8b, run locally). gemini-1.5-pro reached a 72% pass rate versus 54% for gemini-1.5-flash — a +18-point lift.

Base model
gemini-1.5-flash
via google · 54% pass rate
Refined model
gemini-1.5-pro
via google · 72% pass rate · 1.2s p95
Base pass rate
54%
Refined pass rate
72%
Refined p95
1.2s
Est. tokens saved
4.0K
+0pts
refined beats base on 6 rows
0%
Base model
0%
Invoked-refined
2 improved0 regressed4 unchanged

Per-row results

1Detect churn-risk sentiment in a renewal thread0%100%+100
2Route a multi-part ticket to the correct queue100%100%0
3Classify: billing dispute vs refund request vs cancellation0%100%+100
4Extract the affected order id from a free-text complaint100%100%0
5Priority-tag an outage report vs a feature question100%100%0
6Summarize a 12-message thread into a one-line disposition100%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