Prove the lift · AI model performance evaluation
claude-opus-4-8 vs claude-opus-4-6
+2-point lift for claude-opus-4-8 on medical-coding-extract
Test summary
This benchmark evaluates claude-opus-4-8 against claude-opus-4-6 on the medical-coding-extract v3 dataset (5 rows), scored by an LLM-as-judge (llama-3.1-8b). claude-opus-4-8 reached a 54% pass rate versus 52% for claude-opus-4-6 — a +2-point lift.
- Base model
- claude-opus-4-6
- via anthropic · 52% pass rate
- Refined model
- claude-opus-4-8
- via anthropic · 54% pass rate · 2.4s p95
Base pass rate
52%
Refined pass rate
54%
Refined p95
2.4s
Est. tokens saved
8.9K
+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 code0% → 100%+100
2Extract medication + dosage from a clinical note0% → 100%+100
3Determine the correct E/M level from a visit note0% → 100%+100
4Pull the procedure code from an operative report100% → 100%0
5Identify a contraindication from a problem list0% → 0%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