Prove the lift · AI model performance evaluation
gpt-5.1 vs claude-opus-5
+13-point lift for gpt-5.1 on contract-clause-qa
Test summary
This benchmark evaluates gpt-5.1 against claude-opus-5 on the contract-clause-qa v2 dataset (5 rows), scored by an LLM-as-judge (gpt-4o-mini). gpt-5.1 reached a 71% pass rate versus 58% for claude-opus-5 — a +13-point lift.
- Base model
- claude-opus-5
- via anthropic · 58% pass rate
- Refined model
- gpt-5.1
- via openai · 71% pass rate · 3.4s p95
Base pass rate
58%
Refined pass rate
71%
Refined p95
3.4s
Est. tokens saved
1.8K
+0pts
refined beats base on 5 rows
0%
Base model0%
Invoked-refined▲3 improved▼0 regressed●2 unchanged
Per-row results
1Locate the termination-for-convenience terms100% → 100%0
2Identify the governing-law clause and jurisdiction0% → 100%+100
3Find the liability cap and its exceptions0% → 100%+100
4Extract the auto-renewal notice window in days0% → 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 InvokedGenerated with Invoked · Browse all benchmarks