Prove the lift · AI model performance evaluation
gpt-4-turbo vs claude-sonnet-4-6
+11-point lift for gpt-4-turbo on medical-coding-extract
Test summary
This benchmark evaluates gpt-4-turbo against claude-sonnet-4-6 on the medical-coding-extract v3 dataset (5 rows), scored by an LLM-as-judge (gpt-4o-mini). gpt-4-turbo reached a 73% pass rate versus 62% for claude-sonnet-4-6 — a +11-point lift.
- Base model
- claude-sonnet-4-6
- via anthropic · 62% pass rate
- Refined model
- gpt-4-turbo
- via openai · 73% pass rate · 3.5s p95
Base pass rate
62%
Refined pass rate
73%
Refined p95
3.5s
Est. tokens saved
2.2K
+0pts
refined beats base on 5 rows
0%
Base model0%
Invoked-refined▲3 improved▼0 regressed●2 unchanged
Per-row results
1Map a discharge summary to the primary ICD-10 code100% → 100%0
2Determine the correct E/M level from a visit note0% → 100%+100
3Identify a contraindication from a problem list0% → 100%+100
4Pull the procedure code from an operative report0% → 100%+100
5Extract medication + dosage from a clinical note100% → 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 InvokedGenerated with Invoked · Browse all benchmarks