Model benchmark rankings

Compare scores, test time and reference cost across models and reasoning levels.

Tested on our private datasetsWhy we test this way

Data snapshot · 10/13/2026

View plan usage

Gemini 4 ArgonNewWorth a look

79.35Overall

View scores

muse-wonderNewWorth a look

81.55Overall

View scores

claude-opus-5-5

87.55Overall

View scores

Each model shows its best score here. Expand to see other effort levels.39 models · 80 configurations

About the scores

Backend engineering 20% · Frontend interaction 20% · Reasoning 35% · Aesthetics 15% · Maintainability 10%. Each model shows its highest-scoring tested effort for the selected category.

Time and cost follow the selected category. They describe these evaluations, not the speed or price of a typical request.

Explore the tasks About the method

Rank by	Model / Tested effort		Backend engineering	Frontend interaction	Knowledge & reasoning	Visual aesthetics	Maintainability	Time / cost
01	gpt-6-astra xhigh Backend engineering95Frontend interaction96Knowledge & reasoning95Visual aesthetics75Maintainability61	88.80	95	96	95	75	61	83m 56s$7.01
02	claude-opus-5-5NEW max Backend engineering84Frontend interaction89Knowledge & reasoning100Visual aesthetics73Maintainability70	87.55	84	89	100	73	70	33m 57s$3.67
03	claude-fable-5-1 max Backend engineering85Frontend interaction91Knowledge & reasoning95Visual aesthetics80Maintainability68	87.25	85	91	95	80	68	79m 7s$26.15
04	gpt-6.1-solNEW max Backend engineering95Frontend interaction96Knowledge & reasoning90Visual aesthetics66Maintainability70	86.60	95	96	90	66	70	62m 9s$1.69
05	claude-sonnet-5-5NEW xhigh Backend engineering86Frontend interaction89Knowledge & reasoning85Visual aesthetics73Maintainability66	82.30	86	89	85	73	66	48m 32s$2.80
06	claude-opus-5 max Backend engineering70Frontend interaction87Knowledge & reasoning95Visual aesthetics73Maintainability61	81.70	70	87	95	73	61	92m 12s$7.99
07	muse-wonderNEW max Backend engineering82Frontend interaction84Knowledge & reasoning90Visual aesthetics73Maintainability59	81.55	82	84	90	73	59	40m 8s$6.78
08	Gemini 4 ArgonNEW Backend engineering82Frontend interaction84Knowledge & reasoning85Visual aesthetics70Maintainability59	79.35	82	84	85	70	59	46m 48sN/A
09	gpt-6-sol xhigh Backend engineering80Frontend interaction94Knowledge & reasoning75Visual aesthetics75Maintainability66	78.90	80	94	75	75	66	39m 22s$1.10
10	grok-4.7 high Backend engineering87Frontend interaction80Knowledge & reasoning85Visual aesthetics66Maintainability55	78.55	87	80	85	66	55	196m 18s$5.25
11	grok-4.6 xhigh Backend engineering78Frontend interaction80Knowledge & reasoning85Visual aesthetics64Maintainability59	76.85	78	80	85	64	59	144m 16s$2.51
12	claude-opus-4-8 xhigh Backend engineering61Frontend interaction87Knowledge & reasoning90Visual aesthetics68Maintainability55	76.80	61	87	90	68	55	102m 10s$9.18
13	gpt-5.6-sol max Backend engineering85Frontend interaction73Knowledge & reasoning75Visual aesthetics66Maintainability64	74.15	85	73	75	66	64	87m 21s$3.25
14	muse-spark-1.3NEW default Backend engineering73Frontend interaction91Knowledge & reasoning75Visual aesthetics59Maintainability47	72.60	73	91	75	59	47	29m 10s$0.066
15	k3 high Backend engineering70Frontend interaction85Knowledge & reasoning70Visual aesthetics68Maintainability59	71.60	70	85	70	68	59	158m 17s$3.28
16	glm-5.3 max Backend engineering70Frontend interaction78Knowledge & reasoning70Visual aesthetics66Maintainability64	70.40	70	78	70	66	64	153m 15s$1.83
17	mimo-v2.6-pro default Backend engineering70Frontend interaction85Knowledge & reasoning65Visual aesthetics64Maintainability59	69.25	70	85	65	64	59	336m 3s$0.66
18	space-bunny default Backend engineering61Frontend interaction80Knowledge & reasoning75Visual aesthetics59Maintainability55	68.80	61	80	75	59	55	62m 35s$0.000
19	MiniMax-M3.1-Flash-Preview max Backend engineering75Frontend interaction57Knowledge & reasoning75Visual aesthetics70Maintainability53	68.45	75	57	75	70	53	54m 7sN/A
20	deepseek-v4.1-flash max Backend engineering62Frontend interaction88Knowledge & reasoning65Visual aesthetics64Maintainability55	67.85	62	88	65	64	55	35m 40s$0.41
21	hy4-preview high Backend engineering74Frontend interaction73Knowledge & reasoning65Visual aesthetics59Maintainability57	66.70	74	73	65	59	57	218m 41s$1.63
22	gpt-5.6-terra max Backend engineering81Frontend interaction76Knowledge & reasoning55Visual aesthetics61Maintainability61	65.90	81	76	55	61	61	133m 2s$1.94
23	claude-haiku-5-5NEW xhigh Backend engineering69Frontend interaction78Knowledge & reasoning60Visual aesthetics59Maintainability64	65.65	69	78	60	59	64	27m 38s$0.21
24	step-5-preview default Backend engineering61Frontend interaction71Knowledge & reasoning75Visual aesthetics47Maintainability55	65.20	61	71	75	47	55	98m 22s$1.24
25	deepseek-v4-pro max Backend engineering67Frontend interaction63Knowledge & reasoning65Visual aesthetics70Maintainability59	65.15	67	63	65	70	59	93m 15s$1.15
25	Qwen 3.8 Flash default Backend engineering68Frontend interaction87Knowledge & reasoning50Visual aesthetics73Maintainability57	65.15	68	87	50	73	57	134m 31s$0.42
27	k2.8 preview high Backend engineering54Frontend interaction72Knowledge & reasoning70Visual aesthetics57Maintainability53	63.55	54	72	70	57	53	70m 58s$0.66
28	gpt-6-luna xhigh Backend engineering62Frontend interaction80Knowledge & reasoning50Visual aesthetics68Maintainability59	62.00	62	80	50	68	59	63m 52s$0.061
29	deepseek-v4-flash high Backend engineering58Frontend interaction76Knowledge & reasoning55Visual aesthetics61Maintainability53	60.50	58	76	55	61	53	98m 25s$0.42
30	deepseek-v4-flash-vision-exp high Backend engineering61Frontend interaction43Knowledge & reasoning70Visual aesthetics61Maintainability55	59.95	61	43	70	61	55	88m 43s$0.32
31	Gemini 3.8 Flash High default Backend engineering64Frontend interaction86Knowledge & reasoning40Visual aesthetics66Maintainability59	59.80	64	86	40	66	59	25m 21s$0.13
32	glm-5.3-flash max Backend engineering54Frontend interaction75Knowledge & reasoning40Visual aesthetics78Maintainability53	56.80	54	75	40	78	53	102m 55s$0.081
33	mimo-v2.6-flash default Backend engineering58Frontend interaction71Knowledge & reasoning45Visual aesthetics59Maintainability57	56.10	58	71	45	59	57	386m 14s$0.28
34	Qwen 3.8 Max default Backend engineering64Frontend interaction69Knowledge & reasoning40Visual aesthetics64Maintainability53	55.50	64	69	40	64	53	133m 3s$3.41
35	Qwen 3.8 27b default Backend engineering64Frontend interaction87Knowledge & reasoning20Visual aesthetics66Maintainability59	53.00	64	87	20	66	59	104m 31s$1.79
36	MiniMax-M3 high Backend engineering46Frontend interaction65Knowledge & reasoning50Visual aesthetics59Maintainability44	52.95	46	65	50	59	44	56m 33s$0.62
37	gpt-5.6-luna xhigh Backend engineering56Frontend interaction83Knowledge & reasoning25Visual aesthetics66Maintainability59	52.35	56	83	25	66	59	75m 23s$0.16
38	Gemini 3.7 Flash High default Backend engineering63Frontend interaction71Knowledge & reasoning25Visual aesthetics70Maintainability59	51.95	63	71	25	70	59	24m 19s$0.13
39	Nemotron-3-Ultra default Backend engineering46Frontend interaction40Knowledge & reasoning40Visual aesthetics61Maintainability37	44.05	46	40	40	61	37	109m 30s$0.000

Each model uses its highest-scoring effort here. Equal scores share a rank.

Backend engineering 20% · Frontend interaction 20% · Reasoning 35% · Aesthetics 15% · Maintainability 10%. Evaluation scope and sources