Model Releases
Le Chonk cooked on visual grounding. Pinpoints exactly where things are in an image. 42% on Dense 200, ahead of even frontier closed models.…
Mistral AI announced its Le Chonk model, which performs visual grounding by accurately locating objects within images. On the Dense 200 benchmark it achieved a 42 % score, outperforming even frontier‑
Mistral AI announced its Le Chonk model, which performs visual grounding by accurately locating objects within images. On the Dense 200 benchmark it achieved a 42 % score, outperforming even frontier‑closed models. The announcement was made in a tweet posted on October 12, 2026.
Related
Source: Mistral AI (X) | 2026-10-12