Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Subjective Guidance Quality on Ego4D
Loading...
3.94
Subjective Guidance Quality (1-5)
Llama 4-Maverick (PWR)
2.328
2.7465
3.165
3.5835
Jun 3, 2026
Subjective Guidance Quality (1-5)
Updated 1mo ago
Evaluation Results
Method
Method
Links
Subjective Guidance Quality (1-5)
Llama 4-Maverick (PWR)
Config=PWR
2026.06
3.94
Qwen3.6-VL-27B (PWR)
Config=PWR
2026.06
3.55
Llama 4-Maverick
Config=FT
2026.06
2.93
Qwen3.6-VL-27B
Config=ZS
2026.06
2.7
Qwen3-VL-235B
Config=ZS
2026.06
2.48
Claude Opus 4.6
Config=ZS
2026.06
2.47
Gemini 3.1 Pro
Config=ZS
2026.06
2.44
Llama 4-Maverick
Config=ZS
2026.06
2.41
Qwen3.6-VL-27B
Config=FT
2026.06
2.39
Feedback
Search any
task
Search any
task