EvalLedger
Leaderboard
Compare
Token Calculator
Model Releases
Version series
Changelog
EN
Benchmark
BabyVision (w/tools)
Visual perception benchmark, tool-assisted.
Score history →
Model scores
#
Model
Score
1
Claude Opus 5
94.1%
2
DeepSeek V4.1-Flash 1017
92.5%
3
DeepSeek V4.1-Flash 0910
89.6%
4
GPT 5.6-Sol
88.9%
5
Kimi K3
85.7%