Prove the lift · AI model performance evaluation

gemini-1.5-pro vs llama-3.1-70b

+19-point lift for gemini-1.5-pro on contract-clause-qa

Test summary

This benchmark evaluates gemini-1.5-pro against llama-3.1-70b on the contract-clause-qa v2 dataset (5 rows), scored by an LLM-as-judge (claude-haiku-4-5). gemini-1.5-pro reached a 46% pass rate versus 27% for llama-3.1-70b — a +19-point lift.

Base model
llama-3.1-70b
via ollama · 27% pass rate
Refined model
gemini-1.5-pro
via google · 46% pass rate · 1.4s p95
Base pass rate
27%
Refined pass rate
46%
Refined p95
1.4s
Est. tokens saved
10.8K
+0pts
refined beats base on 5 rows
0%
Base model
0%
Invoked-refined
▲2 improved▼0 regressed●3 unchanged

Per-row results

1Find the liability cap and its exceptions0% → 0%0
2Extract the auto-renewal notice window in days0% → 100%+100
3Identify the governing-law clause and jurisdiction0% → 100%+100
4Determine indemnification scope and carve-outs0% → 0%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 Invoked
Generated with Invoked · Browse all benchmarks