ZEROBench_sub
ZEROBench subset - visual reasoning puzzle benchmark.
Category
Vision & Language
Max Score
100.0
Score Type
percent
Active
Yes
Model Scores
Scores for ZEROBench_sub
| Model | Score | Date | Verified |
|---|---|---|---|
| Qwen3.6-35B-A3B |
82.35%
|
16.04.2026 | Verified |
| Gemma4-31B-it |
26.00
|
16.04.2026 | Unverified |
| Qwen3.5-35B-A3B |
79.41%
|
16.04.2026 | Unverified |
| Gemma4-26B-A4B |
2.94%
|
16.04.2026 | Unverified |
| Claude-Sonnet-4.5 |
2.94%
|
16.04.2026 | Unverified |
| Qwen3.5-27B |
100.00%
|
16.04.2026 | Unverified |
| Qwen3.5-4B |
2.94%
|
01.02.2026 | Verified |
| Qwen3.5-122B-A10B |
100.00%
|
01.02.2026 | Verified |
| GPT-5-mini 2025-08-07 |
12.75%
|
01.02.2026 | Unverified |
| Qwen3-235B-A22B |
23.53%
|
01.02.2026 | Unverified |
| Qwen3-VL-235B-A22B |
23.53%
|
01.02.2026 | Verified |