Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Proactive Assistance on Household domain
Loading...
19.1
Speedup
MindZero w/ Qwen3-4B
-3.052
2.699
8.45
14.201
May 29, 2026
Speedup
TFLOPs
Updated 1d ago
Evaluation Results
Method
Method
Links
Speedup
TFLOPs
MindZero w/ Qwen3-4B
Backbone=Qwen3-4B
2026.05
19.1
201.2
Gemini-3-Flash
Category=Large Model
2026.05
17.7
-
MindZero w/ Llama-3.1-8B
Backbone=Llama-3.1-8B
2026.05
17.4
608.4
Qwen3-235B-A22B
Category=Large Model
2026.05
12.3
1,101.6
GPT-5.2
Category=Large Model
2026.05
9.4
-
MindZero w/ Llama-3.2-3B*
Backbone=Llama-3.2-3B,...
2026.05
4.3
235.1
Llama-3.2-3B*
Category=Base Model, r...
2026.05
2.3
244.3
Qwen3-4B
Category=Base Model
2026.05
2.3
213.1
Llama-3.1-8B
Category=Base Model
2026.05
1.7
656.1
Random Goal
2026.05
-2.2
-
Feedback
Search any
task
Search any
task