Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Proactive Assistance on Pro2Bench HoloAssist
Loading...
87
G-Mean F1
Llama 4-Maverick
-3.48
20.01
43.5
66.99
Jun 3, 2026
G-Mean F1
PQS
Updated 1mo ago
Evaluation Results
Method
Method
Links
G-Mean F1
PQS
Llama 4-Maverick
FT=true, PWR=true, Arc...
2026.06
87
65
Qwen3.6-VL-27B
FT=true, PWR=true, Arc...
2026.06
79
45
Llama 4-Maverick
FT=true, Architecture=...
2026.06
71
46
Gemini 3.1 Pro
Architecture=monolithi...
2026.06
53
41
Llama 4-Maverick
Architecture=monolithic
2026.06
50
47
Claude Opus 4.6
Architecture=monolithi...
2026.06
49
26
Qwen3.6-VL-27B
FT=true, Architecture=...
2026.06
49
31
Qwen3-VL-235B
Architecture=monolithic
2026.06
46
35
Qwen3.6-VL-27B
Architecture=monolithic
2026.06
22
41
GPT-5.2
Architecture=monolithi...
2026.06
0
-
Feedback
Search any
task
Search any
task