Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Subjective Guidance Quality on HowTo
Loading...
3.93
Subjective Quality Score
Llama 4-Maverick (PWR)
1.8916
2.4208
2.95
3.4792
Jun 3, 2026
Subjective Quality Score
Updated 1mo ago
Evaluation Results
Method
Method
Links
Subjective Quality Score
Llama 4-Maverick (PWR)
Config=PWR
2026.06
3.93
Llama 4-Maverick
Config=FT
2026.06
2.93
Qwen3.6-VL-27B (PWR)
Config=PWR
2026.06
2.67
Qwen3.6-VL-27B
Config=ZS
2026.06
2.62
Gemini 3.1 Pro
Config=ZS
2026.06
2.41
Qwen3-VL-235B
Config=ZS
2026.06
2.32
Claude Opus 4.6
Config=ZS
2026.06
2.09
Qwen3.6-VL-27B
Config=FT
2026.06
2.08
Llama 4-Maverick
Config=ZS
2026.06
1.97
Feedback
Search any
task
Search any
task