Prove the lift · AI model performance evaluation
llama-4-maverick vs gpt-4.1-mini
-4-point lift for llama-4-maverick on contract-clause-qa
Test summary
This benchmark evaluates llama-4-maverick against gpt-4.1-mini on the contract-clause-qa v2 dataset (5 rows), scored by an LLM-as-judge (claude-haiku-4-5). llama-4-maverick reached a 46% pass rate versus 50% for gpt-4.1-mini — a -4-point lift.
- Base model
- gpt-4.1-mini
- via openai · 50% pass rate
- Refined model
- llama-4-maverick
- via meta · 46% pass rate · 1.0s p95
Base pass rate
50%
Refined pass rate
46%
Refined p95
1.0s
Est. tokens saved
—
−0pts
no lift — the base model held its ground
0%
Base model0%
Invoked-refined▲3 improved▼1 regressed●1 unchanged
Per-row results
1Find the liability cap and its exceptions100% → 0%-100
2Extract the auto-renewal notice window in days0% → 100%+100
3Identify the governing-law clause and jurisdiction0% → 0%0
4Locate the termination-for-convenience terms0% → 100%+100
5Determine indemnification scope and carve-outs0% → 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