Prove the lift · AI model performance evaluation

claude-opus-4-6 vs claude-sonnet-5

+11-point lift for claude-opus-4-6 on contract-clause-qa

Test summary

This benchmark evaluates claude-opus-4-6 against claude-sonnet-5 on the contract-clause-qa v3 dataset (5 rows), scored by an LLM-as-judge (claude-haiku-4-5). claude-opus-4-6 reached a 39% pass rate versus 28% for claude-sonnet-5 — a +11-point lift.

Base model
claude-sonnet-5
via anthropic · 28% pass rate
Refined model
claude-opus-4-6
via anthropic · 39% pass rate · 1.6s p95
Base pass rate
28%
Refined pass rate
39%
Refined p95
1.6s
Est. tokens saved
1.8K
+0pts
refined beats base on 5 rows
0%
Base model
0%
Invoked-refined
1 improved0 regressed4 unchanged

Per-row results

1Find the liability cap and its exceptions0%100%+100
2Extract the auto-renewal notice window in days0%0%0
3Locate the termination-for-convenience terms100%100%0
4Determine indemnification scope and carve-outs0%0%0
5Identify the governing-law clause and jurisdiction100%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