@VikParuchuri: We're open sourcing a 9B model that extracts structured data from documents at near-frontier performance. - 90.2% on ou…
Summary
Vik Paruchuri is open-sourcing a 9B model that extracts structured data from documents with near-frontier performance (90.2% on their benchmark, vs Gemini 3.5 Flash at 91.3%).
View Cached Full Text
Cached at: 06/20/26, 02:35 PM
We’re open sourcing a 9B model that extracts structured data from documents at near-frontier performance.
- 90.2% on our bench, vs Gemini 3.5 Flash at 91.3%
- Leads extraction models like NuExtract3 (81.5%)
- 9.5s p50 timings
- Pass JSON schema https://t.co/zIdRbGjaY5
Similar Articles
Open-source models are closing the coding gap with GPT/Claude/Gemini ~1.5x faster than the frontier is advancing, and on decontaminated benchmarks a 27B model already beats Claude Opus 4.8 [live dashboard + analysis]
A live dashboard and statistical analysis shows open-source coding models are closing the gap with closed models at 1.5x the rate, with a 27B model already surpassing Claude Opus on decontaminated benchmarks. Tool-call reliability remains the main bottleneck.
@VikParuchuri: We're launching turbo mode data extraction - 5x faster, 5x cheaper, and 7% more accurate than Azure Content Understandi…
VikParuchuri announces the launch of turbo mode data extraction, claiming 5x faster and cheaper performance with 7% more accuracy than Azure Content Understanding, achieving competitive latency for real-time workflows.
@googleaidevs: We wanted to see how Gemini 3.5 Flash-Lite handles massive, repetitive visual tasks. This demo runs the model across 1M…
Google AI demonstrates Gemini 3.5 Flash-Lite processing over 1 million catalog images, extracting structured data with low latency and token efficiency for large-scale workflows.
@NielsRogge: That's right, a 3.9GB file getting 99.2% on Math 500 A dataset once introduced by @OpenAI in the paper "Let's verify st…
PrismML's Bonsai-27B model achieves 99.2% on the Math 500 dataset, outperforming DeepSeek-R1 and Kimi K2.
@VikParuchuri: This is lift (our open source extraction model) pulling structured data out of a messy 26-page contract.
Vik Paruchuri showcases lift, an open-source extraction model capable of pulling structured data from messy contracts.