Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Subjective Guidance Quality on EK
Loading...
3.67
Subjective Guidance Quality
Llama 4-Maverick (PWR)
2.11
2.515
2.92
3.325
Jun 3, 2026
Subjective Guidance Quality
Updated 1mo ago
Evaluation Results
Method
Method
Links
Subjective Guidance Quality
Llama 4-Maverick (PWR)
Config=PWR
2026.06
3.67
Llama 4-Maverick
Config=FT
2026.06
3.02
Qwen3.6-VL-27B
Config=ZS
2026.06
2.79
Qwen3.6-VL-27B (PWR)
Config=PWR
2026.06
2.44
Llama 4-Maverick
Config=ZS
2026.06
2.43
Gemini 3.1 Pro
Config=ZS
2026.06
2.35
Qwen3-VL-235B
Config=ZS
2026.06
2.29
Qwen3.6-VL-27B
Config=FT
2026.06
2.18
Claude Opus 4.6
Config=ZS
2026.06
2.17
Feedback
Search any
task
Search any
task