Prove the lift · AI model performance evaluation
llama-3.3-70b vs gpt-4o
+11-point lift for llama-3.3-70b on contract-clause-qa
Test summary
This benchmark evaluates llama-3.3-70b against gpt-4o on the contract-clause-qa v1 dataset (5 rows), scored by an LLM-as-judge (claude-haiku-4-5, run locally). llama-3.3-70b reached a 62% pass rate versus 51% for gpt-4o — a +11-point lift.
- Base model
- gpt-4o
- via openai · 51% pass rate
- Refined model
- llama-3.3-70b
- via meta · 62% pass rate · 1.4s p95
Base pass rate
51%
Refined pass rate
62%
Refined p95
1.4s
Est. tokens saved
3.6K
+0pts
refined beats base on 5 rows
0%
Base model0%
Invoked-refined▲0 improved▼0 regressed●5 unchanged
Per-row results
1Identify the governing-law clause and jurisdiction100% → 100%0
2Extract the auto-renewal notice window in days100% → 100%0
3Determine indemnification scope and carve-outs100% → 100%0
4Find the liability cap and its exceptions100% → 100%0
5Locate the termination-for-convenience terms100% → 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