1.3B open-source MiniCPM-OCR 1.0 tops Real5-OmniDocBench, beating GPT-5.2
NielsRogge · x · 2026-11-11
MiniCPM-OCR 1.0 from OpenBMB takes #1 on Real5-OmniDocBench with 93.68, narrowly beating OvisOCR3 (93.63). The 1.3B open-weights model (Apache 2.0, 99k downloads last month) also outperforms the 1100B Kimi-K2.6 (89.76) and GPT-5.2 (78.66) on real-world captured documents.
More from Models
- OpenAI open-sources mcp-extensions to make plugins feel native to ChatGPT — SIGKITTEN · 2026-11-11
- Logan Kilpatrick questions AI leaderboard: why is only our model not tested in its native harness? — zacharynado · 2026-11-11
- Unverified hands-on claim: 'Gemini Carbon' is frontier-grade but hallucinates and rambles — zacharynado · 2026-11-11
- Top AI models still can't beat the 95.4% human score on word logic puzzles — ChrisGPT · 2026-11-11
- RISJ data: ChatGPT leads AI trust at +17, Grok lowest at -6 — _FelixSimon_ · 2026-11-11
- 7 testers put Gemini 4 Carbon through a Reach Test: 2 would always use it, 1 won't — every · 2026-11-11