Prove the lift · AI model performance evaluation

gpt-4o vs llama-3.1-8b

+24-point lift for gpt-4o on medical-coding-extract

Test summary

This benchmark evaluates gpt-4o against llama-3.1-8b on the medical-coding-extract v2 dataset (5 rows), scored by an LLM-as-judge (claude-haiku-4-5, run locally). gpt-4o reached a 63% pass rate versus 39% for llama-3.1-8b — a +24-point lift.

Base model
llama-3.1-8b
via ollama · 39% pass rate
Refined model
gpt-4o
via openai · 63% pass rate · 0.7s p95
Base pass rate
39%
Refined pass rate
63%
Refined p95
0.7s
Est. tokens saved
10.7K
+0pts
refined beats base on 5 rows
0%
Base model
0%
Invoked-refined
3 improved0 regressed2 unchanged

Per-row results

1Determine the correct E/M level from a visit note100%100%0
2Identify a contraindication from a problem list100%100%0
3Extract medication + dosage from a clinical note0%100%+100
4Map a discharge summary to the primary ICD-10 code0%100%+100
5Pull the procedure code from an operative report0%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