Prove the lift · AI model performance evaluation
claude-sonnet-4-6 vs gemini-1.5-flash
+22-point lift for claude-sonnet-4-6 on medical-coding-extract
Test summary
This benchmark evaluates claude-sonnet-4-6 against gemini-1.5-flash on the medical-coding-extract v2 dataset (5 rows), scored by an LLM-as-judge (gpt-4o-mini, run locally). claude-sonnet-4-6 reached a 62% pass rate versus 40% for gemini-1.5-flash — a +22-point lift.
- Base model
- gemini-1.5-flash
- via google · 40% pass rate
- Refined model
- claude-sonnet-4-6
- via anthropic · 62% pass rate · 1.6s p95
Base pass rate
40%
Refined pass rate
62%
Refined p95
1.6s
Est. tokens saved
3.7K
+0pts
refined beats base on 5 rows
0%
Base model0%
Invoked-refined▲2 improved▼0 regressed●3 unchanged
Per-row results
1Identify a contraindication from a problem list100% → 100%0
2Determine the correct E/M level from a visit note100% → 100%0
3Extract medication + dosage from a clinical note100% → 100%0
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 InvokedGenerated with Invoked · Browse all benchmarks