Prove the lift · AI model performance evaluation

claude-opus-4-6 vs llama-3.1-70b

+19-point lift for claude-opus-4-6 on contract-clause-qa

Test summary

This benchmark evaluates claude-opus-4-6 against llama-3.1-70b on the contract-clause-qa v1 dataset (5 rows), scored by an LLM-as-judge (claude-haiku-4-5). claude-opus-4-6 reached a 53% pass rate versus 34% for llama-3.1-70b — a +19-point lift.

Base model
llama-3.1-70b
via ollama · 34% pass rate
Refined model
claude-opus-4-6
via anthropic · 53% pass rate · 2.1s p95
Base pass rate
34%
Refined pass rate
53%
Refined p95
2.1s
Est. tokens saved
3.9K
+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% → 0%0
4Locate the termination-for-convenience terms0% → 100%+100
5Determine indemnification scope and carve-outs100% → 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