ZEROBench

ZEROBench - visual reasoning puzzle benchmark. Very challenging, scores typically in single digits.

Category

Vision & Language

Max Score

—

Score Type

percent

Active

Yes

Model Scores

Scores for ZEROBench

Model Score Date Verified
Qwen3.5-4B
3.00
01.02.2026 Verified
Kimi K3
82.61%
18.08.2026 Verified
Qwen3.5-122B-A10B
13.04%
01.02.2026 Verified
Qwen3.5-27B
15.22%
01.02.2026 Unverified
Qwen3.5-35B-A3B
10.87%
01.02.2026 Unverified
Claude-Sonnet-4.5
2.17%
01.02.2026 Unverified
GPT-5-mini 2025-08-07
3.00
01.02.2026 Unverified
Qwen3-235B-A22B
2.17%
01.02.2026 Unverified
Qwen3-VL-235B-A22B
2.17%
01.02.2026 Verified
DeepSeek-V4-Flash-Vision-Exp
69.57%
08.09.2026 Verified
Opus-4.8
67.39%
08.09.2026 Verified
DeepSeek-V4.1-Flash
100.00%
10.09.2026 Verified