Prove the lift · AI model performance evaluation

llama-3.1-405b vs gpt-4.1-mini

+24-point lift for llama-3.1-405b on support-ticket-triage

Test summary

This benchmark evaluates llama-3.1-405b against gpt-4.1-mini on the support-ticket-triage v3 dataset (5 rows), scored by an LLM-as-judge (llama-3.1-8b). llama-3.1-405b reached a 59% pass rate versus 35% for gpt-4.1-mini — a +24-point lift.

Base model
gpt-4.1-mini
via openai · 35% pass rate
Refined model
llama-3.1-405b
via meta · 59% pass rate · 3.4s p95
Base pass rate
35%
Refined pass rate
59%
Refined p95
3.4s
Est. tokens saved
12.0K
+0pts
refined beats base on 5 rows
0%
Base model
0%
Invoked-refined
4 improved0 regressed1 unchanged

Per-row results

1Priority-tag an outage report vs a feature question0%100%+100
2Summarize a 12-message thread into a one-line disposition100%100%0
3Classify: billing dispute vs refund request vs cancellation0%100%+100
4Extract the affected order id from a free-text complaint0%100%+100
5Route a multi-part ticket to the correct queue0%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