Loading
Life sciences · Preprint
arXiv · September 3, 2026
The material analysed did not support any firm read.
This is a technical report announcing Mitra-v2, a machine-learning foundation model trained on synthetic tabular data and benchmarked against other models on 300+ datasets including clinical prediction tasks. The report does not present clinical validation, peer review, or evidence that the model improves patient outcomes or clinical decision-making in practice.
Preprint.
Mitra-v2 achieves state-of-the-art performance on TabArena and TALENT benchmarks comprising more than 300 real-world datasets Model matches 1.6B-parameter TabFM with only 77M parameters (5% of size) Surpasses TabPFN-3 by a wide margin in both classification and regression on full TabArena
Safety was not reported in the material analysed. Check the source before drawing any conclusion about harm.
The source did not state who this applies to in practice.
This is a technical model report without clinical validation, peer review, or empirical evidence from actual clinical use; it describes computational performance on benchmarks, not patient outcomes or clinical utility.
Quoted from the source exactly as published.
Graded across the dimensions that decide whether you should act, each from what the source actually supports. There is no single score, and where a dimension was not assessed it says so.
We introduce Mitra-v2, a tabular foundation model that delivers state-of-the-art performance on real-world classification and regression problems, from credit-risk scoring and clinical prediction to equipment-failure detection and house-price estimation. Mitra-v2 is trained only on synthetic data, with a pretraining distribution that is much larger and more diverse than Mitra-v1's. Built on a small 2D Transformer backbone, Mitra-v2 supports longer contexts and larger feature spaces. Improved optimization lets it learn from this larger task distribution. We evaluate Mitra-v2 on the TabArena and TALENT benchmarks, comprising more than 300 real-world datasets under two evaluation protocols. On the full TabArena benchmark, Mitra-v2 delivers state-of-the-art performance at the level of the industry-scale TabFM and EXAONE Tabular models, while surpassing TabPFN-3 by a wide margin in both classification and regression. Mitra-v2 matches the 1.6B-parameter TabFM with only 5% of its size (77M parameters), delivering frontier performance at a fraction of the cost. On TALENT, Mitra-v2 remains among the leading models, clearly outperforming TabPFN-3 and TabICLv2. It also ranks first on classification tasks with more than ten classes, even though it was pretrained only on tasks with at most ten classes. These results make Mitra-v2 one of the strongest and most broadly applicable open tabular foundation models released to date. We release the model weights, the inference and fine-tuning code, and our evaluation results under the Apache-2.0 license.
Taken from the source record, never inferred. Follow any of these and new work involving them reaches your briefing.