Unverified50% confidenceBenchmarkExact time
At the hundred-page document scale, Unlimited OCR 2 achieves a 5.6x per-step speedup over R-SWA.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
10/30/2026
First Seen
Valid until: 1/28/2027
Sources
Related Entities
Related Claims
UnverifiedUnlimited OCR 2 can parse hundreds of pages or even longer documents in a single uninterrupted pass while keeping computational cost constant.65% similarUnverifiedBaidu has open-sourced the Unlimited OCR 2 model.64% similarUnverifiedUnlimited OCR 2 achieves state-of-the-art results on the MPDocBench benchmark.60% similarUnverifiedPartitioning data into 80 bounded stores achieves linear performance at 2.6 ms/file, which is 3.1× faster overall than a single monolithic store.59% similarUnverifiedThe correlation coefficient between VRAM capacity and decoding speed is R=0.41 (moderate correlation), and between total VRAM plus system memory capacity and speed is R=0.13 (essentially no correlation).58% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1113975API
curl https://kongchang.com/api/v1/knowledge/claims/1113975MCP
get_claim(id=1113975)