benchmark
.
space
benchmarks
rankings
compare
voices
transcripts
papers
articles
OCRBench v2 leaderboard
OCRBench v2
1 models tested · Updated 2026-04-14 · Verified sources only
EXAONE 4.5 33B
leads at
63.2%
1
EXAONE 4.5 33B
LG AI Research ·
HuggingFace/LGAI-EXAONE
· 2026-04-14
Beats GPT-5 mini (55.8) on OCR. Trailing Qwen3-VL 32B (68.4).
63.2%