benchmark
.
space
benchmarks
rankings
compare
voices
transcripts
papers
articles
AI2D leaderboard
AI2D
1 models tested · Updated 2026-04-14 · Verified sources only
EXAONE 4.5 33B
leads at
89.0%
1
EXAONE 4.5 33B
LG AI Research ·
HuggingFace/LGAI-EXAONE
· 2026-04-14
Competitive with GPT-5 mini (88.2) and Qwen3-VL 32B (88.9).
89.0%