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

Code readability, organization and the cost of change. 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
GPT-6.2 AstraNEW
Backend engineering97Frontend interaction97Knowledge & reasoning95Visual aesthetics83Maintainability78
93.009797958378—N/A45
02
Claude Fable 5.2NEW
Backend engineering97Frontend interaction96Knowledge & reasoning100Visual aesthetics83Maintainability73
94.0097961008373—N/A…
02
GPT-6.1 Sol
Backend engineering82Frontend interaction94Knowledge & reasoning85Visual aesthetics75Maintainability73
84.458294857573—N/A…
04
Claude Opus 5.5
Backend engineering81Frontend interaction97Knowledge & reasoning100Visual aesthetics73Maintainability70
89.7581971007370—N/A…
04
GPT-6 Astra
Backend engineering92Frontend interaction96Knowledge & reasoning85Visual aesthetics70Maintainability70
86.159296857070—N/A…
06
Claude Fable 5.1
Backend engineering83Frontend interaction91Knowledge & reasoning95Visual aesthetics80Maintainability68
87.408391958068—N/A…
06
Gemini 4 CarbonNEW
Backend engineering90Frontend interaction95Knowledge & reasoning95Visual aesthetics78Maintainability68
89.609095957868—N/A…
06
GLM-5.3
Backend engineering66Frontend interaction80Knowledge & reasoning50Visual aesthetics66Maintainability68
64.106680506668—N/A…
06
GPT-6 Sol
Backend engineering78Frontend interaction88Knowledge & reasoning70Visual aesthetics75Maintainability68
76.407888707568—N/A…
10
Claude Sonnet 5.5
Backend engineering84Frontend interaction86Knowledge & reasoning85Visual aesthetics73Maintainability66
81.958486857366—N/A…
10
Qwen3.8-Flash
Backend engineering59Frontend interaction70Knowledge & reasoning50Visual aesthetics55Maintainability66
58.905970505566—N/A115
12
Claude Haiku 5.5
Backend engineering65Frontend interaction76Knowledge & reasoning60Visual aesthetics59Maintainability64
65.306576605964—N/A…
12
GPT-5.6 Sol
Backend engineering83Frontend interaction73Knowledge & reasoning75Visual aesthetics66Maintainability64
74.108373756664—N/A…
12
GPT-6.1 Terra
Backend engineering53Frontend interaction78Knowledge & reasoning85Visual aesthetics53Maintainability64
71.555378855364—N/A…
12
GPT-6.2 SolNEW
Backend engineering96Frontend interaction91Knowledge & reasoning95Visual aesthetics73Maintainability64
88.909691957364—N/A…
12
HY4NEW
Backend engineering90Frontend interaction77Knowledge & reasoning75Visual aesthetics59Maintainability64
75.809077755964—N/A…
12
Kimi K3.1 ProNEW
Backend engineering81Frontend interaction91Knowledge & reasoning80Visual aesthetics68Maintainability64
80.158191806864—N/A84
18
Claude Opus 5
Backend engineering66Frontend interaction82Knowledge & reasoning95Visual aesthetics73Maintainability61
80.356682957361—N/A…
18
Gemini 4 HydrogenNEW
Backend engineering83Frontend interaction85Knowledge & reasoning85Visual aesthetics70Maintainability61
80.708385857061—N/A91
18
GPT-5.6 Luna
Backend engineering61Frontend interaction74Knowledge & reasoning25Visual aesthetics59Maintainability61
51.456174255961—N/A…
18
GPT-5.6 Terra
Backend engineering78Frontend interaction76Knowledge & reasoning55Visual aesthetics61Maintainability61
66.057876556161—N/A…
18
Grok 4.6
Backend engineering67Frontend interaction71Knowledge & reasoning80Visual aesthetics61Maintainability61
71.356771806161—N/A…
18
Grok 4.7
Backend engineering84Frontend interaction73Knowledge & reasoning80Visual aesthetics59Maintainability61
75.058473805961—N/A…
18
MiniMax M3.1 Flash
Backend engineering70Frontend interaction75Knowledge & reasoning80Visual aesthetics66Maintainability61
73.457075806661—N/A…
25
DeepSeek V4 Pro
Backend engineering64Frontend interaction60Knowledge & reasoning65Visual aesthetics70Maintainability59
63.456460657059—N/A…
25
DeepSeek V4.1 Flash (1017)
Backend engineering60Frontend interaction81Knowledge & reasoning70Visual aesthetics66Maintainability59
69.256081706659—N/A…
25
Gemini 3.7 Flash
Backend engineering59Frontend interaction67Knowledge & reasoning25Visual aesthetics70Maintainability59
50.205967257059—N/A…
25
Gemini 3.8 Flash
Backend engineering60Frontend interaction84Knowledge & reasoning40Visual aesthetics66Maintainability59
59.506084406659—N/A…
25
Gemini 4 Argon
Backend engineering79Frontend interaction82Knowledge & reasoning85Visual aesthetics70Maintainability59
78.957982857059—N/A…
25
GLM-5.3-Flash
Backend engineering50Frontend interaction69Knowledge & reasoning20Visual aesthetics70Maintainability59
47.155069207059—N/A…
25
GPT-6 Luna
Backend engineering57Frontend interaction78Knowledge & reasoning50Visual aesthetics68Maintainability59
61.105778506859—N/A…
25
Kimi K3
Backend engineering65Frontend interaction82Knowledge & reasoning70Visual aesthetics68Maintainability59
70.706582706859—N/A…
25
MiMo-V2.6-Pro
Backend engineering66Frontend interaction81Knowledge & reasoning65Visual aesthetics64Maintainability59
68.506681656459—N/A…
25
Muse Wonder
Backend engineering78Frontend interaction80Knowledge & reasoning90Visual aesthetics73Maintainability59
80.307880907359—N/A…
25
Qwen3.8-27B
Backend engineering59Frontend interaction85Knowledge & reasoning20Visual aesthetics66Maintainability59
52.555985206659—N/A…
25
Qwen4-Max-PreviewNEW
Backend engineering80Frontend interaction78Knowledge & reasoning90Visual aesthetics59Maintainability59
78.808078905959—N/A84
37
DeepSeek V4.1 Flash (0910)
Backend engineering50Frontend interaction40Knowledge & reasoning50Visual aesthetics61Maintainability57
49.305040506157—N/A…
37
ERNIE 5.5 Flash PreviewNEW
Backend engineering52Frontend interaction52Knowledge & reasoning90Visual aesthetics66Maintainability57
67.205252906657—N/A80
37
HY4 Preview
Backend engineering69Frontend interaction67Knowledge & reasoning65Visual aesthetics59Maintainability57
64.906967655957—N/A…
37
Ling-3.2-FlashNEW
Backend engineering59Frontend interaction54Knowledge & reasoning60Visual aesthetics61Maintainability57
58.105954606157—N/A…
37
MiMo-V2.6-Flash
Backend engineering54Frontend interaction67Knowledge & reasoning45Visual aesthetics59Maintainability57
54.905467455957—N/A…
37
Qwen3.8-Max
Backend engineering65Frontend interaction67Knowledge & reasoning65Visual aesthetics61Maintainability57
64.306567656157—N/A59
43
Claude Opus 4.8
Backend engineering56Frontend interaction85Knowledge & reasoning90Visual aesthetics68Maintainability55
76.255685906855—N/A…
43
DeepSeek V4 Flash Vision Exp
Backend engineering57Frontend interaction39Knowledge & reasoning70Visual aesthetics61Maintainability55
57.255739706155—N/A…
43
QoDuckNEW
Backend engineering70Frontend interaction80Knowledge & reasoning85Visual aesthetics64Maintainability55
75.657080856455—N/A95
43
Space Bunny
Backend engineering57Frontend interaction74Knowledge & reasoning75Visual aesthetics59Maintainability55
67.555774755955—N/A…
43
Step-5 Preview
Backend engineering56Frontend interaction61Knowledge & reasoning75Visual aesthetics47Maintainability55
62.905661754755—N/A…
48
Crouton AlphaNEW
Backend engineering45Frontend interaction64Knowledge & reasoning45Visual aesthetics59Maintainability53
51.954564455953—N/A553
48
DeepSeek V4 Flash
Backend engineering53Frontend interaction67Knowledge & reasoning55Visual aesthetics61Maintainability53
58.005367556153—N/A…
48
Kimi K2.8 (Coding)
Backend engineering55Frontend interaction65Knowledge & reasoning70Visual aesthetics57Maintainability53
62.755565705753—N/A…
48
LongCat-2.5NEW
Backend engineering44Frontend interaction62Knowledge & reasoning75Visual aesthetics55Maintainability53
61.354462755553—N/A…
48
MiniMax M3.1 Flash Preview
Backend engineering71Frontend interaction53Knowledge & reasoning75Visual aesthetics70Maintainability53
66.007153757053—N/A…
53
Egg AlphaNEW
Backend engineering65Frontend interaction78Knowledge & reasoning85Visual aesthetics61Maintainability51
73.456578856151—N/A95
54
Doubao Seed 2.1 Pro (260915)
Backend engineering64Frontend interaction61Knowledge & reasoning55Visual aesthetics68Maintainability49
59.006461556849—N/A…
55
Muse Spark 1.3
Backend engineering68Frontend interaction85Knowledge & reasoning75Visual aesthetics59Maintainability47
71.706885755947—N/A…
56
MiniMax M3
Backend engineering43Frontend interaction59Knowledge & reasoning50Visual aesthetics59Maintainability44
51.154359505944—N/A…
57
NVIDIA Nemotron 3 Ultra (550B-A55B)
Backend engineering42Frontend interaction34Knowledge & reasoning40Visual aesthetics61Maintainability37
40.704234406137—N/A…
Each model uses its highest-scoring effort here. Tied scores share a rank.

Evaluation methodology

Code readability, organization and the cost of change.