Compare capability scores, evaluation time, and cost across models and reasoning efforts.

Evaluated on private datasetsMethodology

Data snapshot · 11/13/2026

Scoring dimension
About the scores

Service logic, error handling and verification. By default, each model shows its highest-scoring tested effort for the selected dimension.

Evaluation time and cost correspond to the selected dimension. They reflect benchmark runs, not everyday single-request latency or billing.

Explore evaluation tasksEvaluation method
Filters
Result scope
57 models · 121 configsBest effort per model

Scroll horizontally to view all scores and costs →

RankModelEval. time
Speed tok/sActions
01
Claude Fable 5.2NEW
Backend engineering97Frontend interaction96Knowledge & reasoning100Visual aesthetics83Maintainability73
94.0097961008373228m 38s$54.15…
01
GPT-6.2 AstraNEW
Backend engineering97Frontend interaction97Knowledge & reasoning95Visual aesthetics83Maintainability78
93.00979795837832m 35sN/A45
03
GPT-6.2 SolNEW
Backend engineering96Frontend interaction91Knowledge & reasoning95Visual aesthetics73Maintainability64
88.90969195736422m 42sN/A…
04
GPT-6 Astra
Backend engineering95Frontend interaction94Knowledge & reasoning95Visual aesthetics75Maintainability61
89.35959495756130m 42s$3.35…
04
GPT-6.1 Sol
Backend engineering95Frontend interaction96Knowledge & reasoning90Visual aesthetics66Maintainability70
88.10959690667032m 36s$1.06…
06
Gemini 4 CarbonNEW
Backend engineering90Frontend interaction95Knowledge & reasoning95Visual aesthetics78Maintainability68
89.609095957868—N/A…
06
HY4NEW
Backend engineering90Frontend interaction77Knowledge & reasoning75Visual aesthetics59Maintainability64
75.80907775596448m 48sN/A…
08
GPT-6.1 Terra
Backend engineering89Frontend interaction84Knowledge & reasoning85Visual aesthetics64Maintainability61
81.0589848564617m 56s$0.38…
09
Grok 4.7
Backend engineering87Frontend interaction74Knowledge & reasoning85Visual aesthetics66Maintainability55
77.75877485665577m 29s$2.00…
10
Claude Sonnet 5.5
Backend engineering84Frontend interaction86Knowledge & reasoning85Visual aesthetics73Maintainability66
81.95848685736615m 3s$1.50…
11
Claude Fable 5.1
Backend engineering83Frontend interaction91Knowledge & reasoning95Visual aesthetics80Maintainability68
87.40839195806843m 45s$12.77…
11
Gemini 4 HydrogenNEW
Backend engineering83Frontend interaction85Knowledge & reasoning85Visual aesthetics70Maintainability61
80.7083858570613m 51s$0.7591
11
GPT-5.6 Sol
Backend engineering83Frontend interaction73Knowledge & reasoning75Visual aesthetics66Maintainability64
74.10837375666429m 19s$1.71…
14
Claude Opus 5.5
Backend engineering81Frontend interaction97Knowledge & reasoning100Visual aesthetics73Maintainability70
89.75819710073709m 29s$1.05…
14
Kimi K3.1 ProNEW
Backend engineering81Frontend interaction91Knowledge & reasoning80Visual aesthetics68Maintainability64
80.15819180686442m 34s$1.8784
16
Qwen4-Max-PreviewNEW
Backend engineering80Frontend interaction78Knowledge & reasoning90Visual aesthetics59Maintainability59
78.80807890595918m 36sN/A84
17
Gemini 4 Argon
Backend engineering79Frontend interaction82Knowledge & reasoning85Visual aesthetics70Maintainability59
78.95798285705914m 48sN/A…
18
GPT-5.6 Terra
Backend engineering78Frontend interaction76Knowledge & reasoning55Visual aesthetics61Maintainability61
66.05787655616175m 45s$0.70…
18
GPT-6 Sol
Backend engineering78Frontend interaction88Knowledge & reasoning70Visual aesthetics75Maintainability68
76.40788870756818m 25s$0.56…
18
Muse Wonder
Backend engineering78Frontend interaction80Knowledge & reasoning90Visual aesthetics73Maintainability59
80.30788090735914m 35s$2.53…
21
Grok 4.6
Backend engineering75Frontend interaction76Knowledge & reasoning85Visual aesthetics64Maintainability59
76.05757685645943m 8s$0.71…
22
MiniMax M3.1 Flash Preview
Backend engineering71Frontend interaction53Knowledge & reasoning75Visual aesthetics70Maintainability53
66.00715375705318m 35sN/A…
23
Claude Opus 5
Backend engineering70Frontend interaction82Knowledge & reasoning85Visual aesthetics66Maintainability59
76.75708285665918m 42s$2.01…
23
MiniMax M3.1 Flash
Backend engineering70Frontend interaction75Knowledge & reasoning80Visual aesthetics66Maintainability61
73.45707580666130m 52s$0.11…
23
QoDuckNEW
Backend engineering70Frontend interaction80Knowledge & reasoning85Visual aesthetics64Maintainability55
75.65708085645516m 27sN/A95
26
DeepSeek V4.1 Flash (1017)
Backend engineering69Frontend interaction91Knowledge & reasoning75Visual aesthetics61Maintainability53
74.20699175615315m 16s$0.12…
26
HY4 Preview
Backend engineering69Frontend interaction67Knowledge & reasoning65Visual aesthetics59Maintainability57
64.90696765595767m 39s$0.40…
28
Muse Spark 1.3
Backend engineering68Frontend interaction85Knowledge & reasoning75Visual aesthetics59Maintainability47
71.7068857559476m 23s$0.024…
29
GLM-5.3
Backend engineering67Frontend interaction72Knowledge & reasoning70Visual aesthetics66Maintainability64
68.90677270666417m 14s$0.44…
30
MiMo-V2.6-Pro
Backend engineering66Frontend interaction81Knowledge & reasoning65Visual aesthetics64Maintainability59
68.50668165645980m 5s$0.18…
31
Claude Haiku 5.5
Backend engineering65Frontend interaction76Knowledge & reasoning60Visual aesthetics59Maintainability64
65.3065766059648m 11s$0.077…
31
Egg AlphaNEW
Backend engineering65Frontend interaction78Knowledge & reasoning85Visual aesthetics61Maintainability51
73.45657885615117m 7sN/A95
31
Kimi K3
Backend engineering65Frontend interaction82Knowledge & reasoning70Visual aesthetics68Maintainability59
70.70658270685937m 56s$0.89…
31
Qwen3.8-Max
Backend engineering65Frontend interaction67Knowledge & reasoning65Visual aesthetics61Maintainability57
64.30656765615759m 27s$1.0359
35
DeepSeek V4 Flash Vision Exp
Backend engineering64Frontend interaction15Knowledge & reasoning65Visual aesthetics—Maintainability—
—641565——14m 12s$0.11…
35
DeepSeek V4 Pro
Backend engineering64Frontend interaction60Knowledge & reasoning65Visual aesthetics70Maintainability59
63.45646065705926m 53s$0.44…
35
Doubao Seed 2.1 Pro (260915)
Backend engineering64Frontend interaction61Knowledge & reasoning55Visual aesthetics68Maintainability49
59.00646155684919m 43s$0.45…
38
GPT-5.6 Luna
Backend engineering61Frontend interaction74Knowledge & reasoning25Visual aesthetics59Maintainability61
51.45617425596148m 26s$0.17…
39
Claude Opus 4.8
Backend engineering60Frontend interaction88Knowledge & reasoning85Visual aesthetics68Maintainability55
76.05608885685563m 16s$8.37…
39
Gemini 3.8 Flash
Backend engineering60Frontend interaction84Knowledge & reasoning40Visual aesthetics66Maintainability59
59.50608440665913m 35s$0.061…
41
Gemini 3.7 Flash
Backend engineering59Frontend interaction67Knowledge & reasoning25Visual aesthetics70Maintainability59
50.2059672570595m 56s$0.069…
41
Ling-3.2-FlashNEW
Backend engineering59Frontend interaction54Knowledge & reasoning60Visual aesthetics61Maintainability57
58.10595460615714m 0sN/A…
41
Qwen3.8-27B
Backend engineering59Frontend interaction85Knowledge & reasoning20Visual aesthetics66Maintainability59
52.55598520665922m 59s$0.43…
41
Qwen3.8-Flash
Backend engineering59Frontend interaction70Knowledge & reasoning50Visual aesthetics55Maintainability66
58.90597050556650m 1s$0.10115
45
DeepSeek V4.1 Flash (0910)
Backend engineering57Frontend interaction78Knowledge & reasoning65Visual aesthetics64Maintainability55
65.55577865645512m 33s$0.10…
45
GPT-6 Luna
Backend engineering57Frontend interaction78Knowledge & reasoning50Visual aesthetics68Maintainability59
61.10577850685917m 54s$0.023…
45
Space Bunny
Backend engineering57Frontend interaction74Knowledge & reasoning75Visual aesthetics59Maintainability55
67.55577475595519m 33s$0.000…
48
Step-5 Preview
Backend engineering56Frontend interaction61Knowledge & reasoning75Visual aesthetics47Maintainability55
62.9056617547557m 12s$0.34…
49
Kimi K2.8 (Coding)
Backend engineering55Frontend interaction65Knowledge & reasoning70Visual aesthetics57Maintainability53
62.75556570575322m 14s$0.21…
50
DeepSeek V4 Flash
Backend engineering54Frontend interaction55Knowledge & reasoning55Visual aesthetics61Maintainability47
54.60545555614714m 8s$0.12…
50
MiMo-V2.6-Flash
Backend engineering54Frontend interaction67Knowledge & reasoning45Visual aesthetics59Maintainability57
54.90546745595735m 36s$0.043…
52
ERNIE 5.5 Flash PreviewNEW
Backend engineering52Frontend interaction52Knowledge & reasoning90Visual aesthetics66Maintainability57
67.20525290665710m 10s$0.07980
52
GLM-5.3-Flash
Backend engineering52Frontend interaction71Knowledge & reasoning40Visual aesthetics70Maintainability53
54.45527140705324m 14s$0.023…
54
Crouton AlphaNEW
Backend engineering45Frontend interaction64Knowledge & reasoning45Visual aesthetics59Maintainability53
51.9545644559531m 22sN/A553
55
LongCat-2.5NEW
Backend engineering44Frontend interaction62Knowledge & reasoning75Visual aesthetics55Maintainability53
61.35446275555339m 17s$0.21…
56
MiniMax M3
Backend engineering43Frontend interaction59Knowledge & reasoning50Visual aesthetics59Maintainability44
51.15435950594422m 6s$0.31…
57
NVIDIA Nemotron 3 Ultra (550B-A55B)
Backend engineering42Frontend interaction34Knowledge & reasoning40Visual aesthetics61Maintainability37
40.70423440613717m 3s$0.000…
Each model uses its highest-scoring effort here. Tied scores share a rank.

Evaluation methodology

Service logic, error handling and verification.