Surya team ships 650M OCR model after 70 RL steps, admits it's just benchmark formatting
VikParuchuri · x · 2026-10-13
VikParuchuri (Surya) released a 650M-param document parsing model that ranks 3rd on LlamaIndex's ParseBench after 70 steps of RL. He cautions the training only aligned output formatting to the benchmark, so it isn't actually better at OCR than Surya OCR 2. The team also introduced OmniParseBench, which will be updated to track the field, borrowing tests from olmOCR bench and documents from ParseBench and other OCR benchmarks for diversity.
Related event: Datalab Launches OmniParseBench and Exposes Benchmark Gaming in OCR(3 posts)→
More from Models
- OpenAI models seem 'lobotomized' on weekdays, developer complains — sterlingcrispin · 2026-10-13
- Muse Wonder scores ~42% on senior engineer benchmark vs Sol 6.1's 71% — danshipper · 2026-10-13
- Zuckerberg unveils Muse Wonder, a frontier model family for agentic work — RebeccaBellan · 2026-10-13
- OpenAI's Decisions API hits 98.1% F1 vs agent's 93.5% at 1/7 cost and 28x lower p90 latency — OpenAIDevs · 2026-10-13
- Alexandr Wang admits Muse Wonder wasn't trained on 3D game demos, insists it excels at real coding — alexandr_wang · 2026-10-13
- Leaked terms suggest X Premium + Grok + Cursor bundled subscription: social, AI and IDE in one plan — ns123abc · 2026-10-13