David A Flood on Mythryl: “I've just published Paleo-Bench a simple multi-modal bench test for…”

I've just published Paleo-Bench a simple multi-modal bench test for how current frontier models transcribe Greek minuscule manuscripts. d-flood.github.io/paleo-bench/ You can see the human transcribed transcription side by side with the model transcription and with IIIF image viewer.

d-flood.github.ioPaleo Bench | HTR Model LeaderboardCompare handwritten Greek text recognition performance across LLM vision models with ranking, CER/WER quality, latency, and cost metrics.

24/2/26, 11:37 pm2 reposts6 likes

Post