List your company

Subjective Guidance Quality on HowTo

3.93Subjective Quality ScoreLlama 4-Maverick (PWR)
1.89162.42082.953.4792Jun 3, 2026

Evaluation results

MethodLinks
Llama 4-Maverick (PWR)Config=PWR2026.063.93
Llama 4-MaverickConfig=FT2026.062.93
Qwen3.6-VL-27B (PWR)Config=PWR2026.062.67
Qwen3.6-VL-27BConfig=ZS2026.062.62
Gemini 3.1 ProConfig=ZS2026.062.41
Qwen3-VL-235BConfig=ZS2026.062.32
Claude Opus 4.6Config=ZS2026.062.09
Qwen3.6-VL-27BConfig=FT2026.062.08
Llama 4-MaverickConfig=ZS2026.061.97