Prove the lift · AI model performance evaluation
mistral-large vs llama-3.1-8b
+16-point lift for mistral-large on medical-coding-extract
Test summary
This benchmark evaluates mistral-large against llama-3.1-8b on the medical-coding-extract v3 dataset (5 rows), scored by an LLM-as-judge (claude-haiku-4-5). mistral-large reached a 43% pass rate versus 27% for llama-3.1-8b — a +16-point lift.
- Base model
- llama-3.1-8b
- via ollama · 27% pass rate
- Refined model
- mistral-large
- via mistral · 43% pass rate · 2.9s p95
Base pass rate
27%
Refined pass rate
43%
Refined p95
2.9s
Est. tokens saved
10.6K
+0pts
refined beats base on 5 rows
0%
Base model0%
Invoked-refined▲2 improved▼0 regressed●3 unchanged
Per-row results
1Map a discharge summary to the primary ICD-10 code0% → 100%+100
2Extract medication + dosage from a clinical note0% → 0%0
3Identify a contraindication from a problem list0% → 0%0
4Determine the correct E/M level from a visit note0% → 100%+100
5Pull the procedure code from an operative report0% → 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