Task

Detailed breakdown of individual task performance across different models.

claude-4-6-sonnet	deepseek-4-pro	gemini-3.1-pro	gemini-3.5-flash	glm-5.1
525.7s	600.2s	128.0s	270.6s	303.8s
161.7s	356.9s	73.9s	166.6s	292.2s
566.0s	600.2s	142.5s	423.4s	600.4s
141.9s	221.9s	56.6s	369.5s	377.7s
600.4s	600.4s	600.3s	495.6s	600.3s
119.3s	270.0s	73.5s	124.0s	144.1s
542.8s	600.2s	253.7s	179.8s	600.3s
528.0s	574.1s	158.7s	236.7s	600.2s
335.8s	521.1s	80.1s	118.6s	303.6s
592.4s	596.0s	121.7s	600.2s	303.7s
315.2s	473.7s	269.8s	587.3s	303.9s
108.9s	250.4s	183.6s	133.8s	342.6s
344.9s	435.8s	329.0s	234.5s	303.9s
600.2s	600.2s	41.5s	600.2s	303.4s
153.1s	168.8s	91.9s	600.2s	577.9s

Loading tasks...