Task

Detailed breakdown of individual task performance across different models.

claude-4-6-sonnet	claude-opus-4-6	gemini-3-flash	gemini-3.1-pro	glm-4.7	gpt-5.2-codex	gpt-5.4	kimi-k2.5
33.1s	32.6s	34.9s	48.1s	223.2s	50.8s	34.6s	108.0s
306.5s	100.9s	21.0s	56.4s	120.6s	52.2s	43.8s	96.0s
26.7s	28.2s	36.6s	46.1s	87.9s	24.6s	23.0s	43.7s
14.7s	296.4s	226.6s	284.7s	113.5s	57.2s	90.0s	436.2s
36.7s	25.0s	30.7s	21.8s	183.5s	32.8s	23.0s	81.2s
16.8s	108.7s	102.7s	98.6s	99.8s	51.3s	34.1s	262.7s
159.2s	380.9s	115.9s	107.2s	600.0s	362.4s	58.9s	77.4s
183.2s	431.8s	600.0s	123.3s	600.0s	73.8s	54.1s	197.2s
24.2s	29.0s	44.3s	26.5s	116.7s	20.1s	23.9s	80.6s
185.3s	173.9s	68.1s	600.0s	76.8s	64.0s	41.6s	204.5s
18.6s	251.0s	513.1s	248.4s	376.8s	187.9s	55.2s	534.7s
126.3s	216.6s	128.4s	200.0s	503.3s	99.4s	95.9s	307.5s
111.4s	251.9s	19.2s	189.5s	326.6s	225.5s	41.0s	119.4s
88.9s	136.2s	91.9s	132.0s	600.0s	53.5s	41.2s	122.5s
18.9s	214.5s	70.5s	20.8s	470.0s	64.5s	49.2s	116.5s
2.7s	3.0s	3.2s	2.5s	2.6s	2.7s	3.7s	3.0s
17.4s	144.5s	19.2s	91.3s	600.0s	108.1s	42.6s	251.4s
80.5s	169.0s	58.3s	150.3s	266.6s	41.1s	41.8s	158.6s
74.5s	129.9s	132.0s	70.3s	600.0s	91.5s	38.6s	87.2s
49.4s	63.4s	48.9s	76.0s	232.4s	56.1s	22.8s	114.2s
108.4s	257.5s	52.5s	57.0s	320.6s	91.7s	37.3s	260.9s
62.1s	97.1s	44.2s	62.7s	155.9s	45.6s	37.0s	48.7s
39.1s	65.0s	34.1s	77.2s	147.9s	31.6s	38.3s	64.6s
364.0s	113.2s	20.7s	147.6s	139.9s	54.6s	41.2s	74.1s
93.6s	95.3s	62.3s	73.6s	600.0s	30.8s	42.2s	12.0s
88.7s	137.7s	85.8s	81.6s	600.0s	117.7s	77.6s	157.4s
35.8s	58.6s	43.7s	40.6s	127.2s	44.5s	30.9s	33.7s
69.7s	322.4s	186.8s	94.3s	600.0s	40.1s	32.3s	12.0s
9.8s	187.7s	18.2s	73.0s	131.6s	46.0s	39.1s	63.8s
120.9s	101.0s	404.0s	96.3s	166.2s	53.0s	39.6s	81.0s
38.0s	99.5s	53.4s	69.6s	182.7s	33.7s	30.5s	126.3s
98.3s	226.3s	92.5s	110.8s	197.3s	109.4s	48.2s	142.6s
96.5s	167.9s	113.6s	84.1s	98.9s	105.8s	23.2s	69.4s
59.2s	69.0s	57.8s	49.8s	92.8s	32.6s	26.7s	45.5s
31.6s	47.9s	369.4s	57.9s	65.9s	14.4s	31.9s	27.7s
83.6s	189.9s	56.9s	77.3s	483.6s	48.7s	33.2s	54.7s
17.2s	238.4s	81.3s	147.9s	483.4s	71.1s	35.1s	11.8s
155.4s	220.4s	174.4s	145.5s	39.8s	81.4s	46.3s	100.7s
62.1s	165.2s	33.4s	34.5s	128.2s	49.2s	25.0s	67.0s
153.7s	269.0s	179.2s	30.4s	35.1s	65.3s	15.7s	178.1s
44.3s	50.4s	107.3s	88.0s	286.6s	48.8s	30.2s	63.6s
331.2s	287.7s	163.4s	74.1s	363.0s	144.4s	72.6s	12.8s
96.7s	325.1s	221.7s	257.0s	55.6s	200.4s	48.6s	162.2s
181.6s	337.3s	209.2s	600.0s	255.9s	170.8s	51.4s	145.9s
4.2s	4.3s	4.6s	4.6s	4.4s	4.8s	4.7s	4.7s
152.4s	382.9s	187.2s	21.1s	363.5s	273.0s	115.3s	142.6s
82.3s	238.5s	122.7s	164.7s	38.3s	60.9s	14.4s	11.3s
62.6s	132.7s	5.3s	184.9s	154.4s	86.4s	33.1s	38.2s
122.6s	168.1s	115.3s	600.0s	59.2s	49.0s	46.5s	86.0s
117.1s	243.5s	96.1s	600.0s	303.3s	169.1s	52.9s	78.4s
3.5s	3.7s	3.6s	3.2s	3.6s	3.2s	3.4s	3.5s
70.3s	171.9s	92.3s	66.5s	600.0s	59.0s	45.3s	46.0s
90.3s	15.2s	53.8s	211.5s	98.1s	78.2s	46.9s	50.8s
81.5s	180.1s	125.5s	600.0s	82.7s	78.8s	37.1s	35.3s
102.5s	138.9s	98.3s	152.9s	98.7s	75.1s	56.1s	29.6s
67.3s	126.6s	45.9s	48.4s	54.0s	29.1s	36.6s	13.1s
16.2s	261.8s	43.7s	65.8s	98.7s	39.9s	31.7s	10.9s
16.7s	154.3s	85.8s	136.5s	112.4s	81.4s	20.0s	131.4s
75.6s	82.7s	43.2s	107.9s	82.8s	37.2s	30.7s	11.2s
118.0s	184.0s	78.8s	188.2s	82.9s	79.8s	18.9s	10.9s
128.6s	199.4s	44.9s	161.6s	68.8s	172.8s	66.9s	12.6s
83.1s	120.8s	182.1s	92.3s	508.0s	182.1s	55.9s	12.4s
78.1s	105.1s	61.7s	66.2s	68.4s	41.2s	29.5s	10.7s