Prove the lift · AI model performance evaluation

claude-sonnet-5 vs claude-opus-4-6

+17-point lift for claude-sonnet-5 on medical-coding-extract

Test summary

This benchmark evaluates claude-sonnet-5 against claude-opus-4-6 on the medical-coding-extract v2 dataset (5 rows), scored by an LLM-as-judge (claude-haiku-4-5). claude-sonnet-5 reached a 77% pass rate versus 60% for claude-opus-4-6 — a +17-point lift.

Base model
claude-opus-4-6
via anthropic · 60% pass rate
Refined model
claude-sonnet-5
via anthropic · 77% pass rate · 0.6s p95
Base pass rate
60%
Refined pass rate
77%
Refined p95
0.6s
Est. tokens saved
3.0K
+0pts
refined beats base on 5 rows
0%
Base model
0%
Invoked-refined
4 improved0 regressed1 unchanged

Per-row results

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