@jerryjliu0
We benchmarked GPT-5.5 on document understanding šš We ran it through ParseBench, our comprehensive OCR benchmark over enterprise documents. We evaluated metrics across various dimensions: visual grounding, tables, charts, and more. We evaluated GPT-5.5 on mid thinking and zero-thinking modes. When compared against GPT-5.4 (0 thinking) and Opus 4.7 (adaptive thinking): š GPT-5.5 wins on tables š GPT-5.5 wins on visual grounding š GPT-5.5 0-thinking does worse on charts than GPT-5.4 0-thinking š Higher thinking does worse than lower thinking of content faithfulness, semantic formatting š Opus 4.7 wins overall on content faithfulness and semantic formatting šø GPT-5.5 is expensive: 13c per page at mid-thinking modes and 5.93 at 0-thinking! This is 5x the cost of any competitive OCR solution. Conclusion: GPT-5.5 is one of the better frontier models out there in terms of pure accuracy, but def not pound for pound w.r.t price.