Prove the lift · AI model performance evaluation
gemini-2.5-pro vs claude-opus-4-6
+8-point lift for gemini-2.5-pro on financial-doc-extract
Test summary
This benchmark evaluates gemini-2.5-pro against claude-opus-4-6 on the financial-doc-extract v2 dataset (5 rows), scored by an LLM-as-judge (claude-haiku-4-5). gemini-2.5-pro reached a 65% pass rate versus 57% for claude-opus-4-6 — a +8-point lift.
- Base model
- claude-opus-4-6
- via anthropic · 57% pass rate
- Refined model
- gemini-2.5-pro
- via google · 65% pass rate · 0.5s p95
Base pass rate
57%
Refined pass rate
65%
Refined p95
0.5s
Est. tokens saved
1.2K
+0pts
refined beats base on 5 rows
0%
Base model0%
Invoked-refined▲2 improved▼0 regressed●3 unchanged
Per-row results
1Identify a going-concern note in the footnotes100% → 100%0
2Determine the reporting period from a 10-Q header100% → 100%0
3Extract total debt from a balance sheet0% → 100%+100
4Extract net revenue and YoY change from an earnings PDF100% → 100%0
5Pull the diluted EPS from an income statement0% → 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