Model benchmark rankings

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

Evaluated on private datasetsWhy we test this way

Data snapshot · 10/27/2026

Scoring dimension
About the scores

Cross-disciplinary knowledge and complex problem solving. By default, each model shows its highest-scoring tested effort for the selected dimension.

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

Explore evaluation tasksEvaluation method
Filters
Result scope
44 models · 105 configsBest effort per model

Scroll horizontally to view all scores and costs →

RankModelEval. time
Speed tok/sActions
01
claude-opus-5-5
Backend engineering84Frontend interaction97Knowledge & Reasoning100Visual aesthetics73Maintainability70
89.15849710073708m 24s$0.25…
02
claude-fable-5-1
Backend engineering85Frontend interaction91Knowledge & Reasoning95Visual aesthetics80Maintainability68
87.2585919580689m 12s$6.70…
02
claude-opus-5
Backend engineering70Frontend interaction87Knowledge & Reasoning95Visual aesthetics73Maintainability61
81.70708795736140m 24s$1.66…
02
gpt-6-astra
Backend engineering95Frontend interaction96Knowledge & Reasoning95Visual aesthetics75Maintainability61
88.80959695756136m 53s$2.16…
05
claude-opus-4-8
Backend engineering61Frontend interaction87Knowledge & Reasoning90Visual aesthetics68Maintainability55
76.80618790685540m 31s$2.20…
05
gpt-6.1-sol
Backend engineering95Frontend interaction96Knowledge & Reasoning90Visual aesthetics66Maintainability70
86.6095969066705m 7s$0.41…
05
muse-wonder
Backend engineering82Frontend interaction84Knowledge & Reasoning90Visual aesthetics73Maintainability59
81.55828490735919m 2s$3.37…
08
claude-sonnet-5-5
Backend engineering86Frontend interaction89Knowledge & Reasoning85Visual aesthetics73Maintainability66
82.3086898573663m 44s$0.13…
08
Gemini 4 Argon
Backend engineering82Frontend interaction84Knowledge & Reasoning85Visual aesthetics70Maintainability59
79.35828485705912m 5sN/A…
08
gpt-6.1-terraNEW
Backend engineering89Frontend interaction84Knowledge & Reasoning85Visual aesthetics64Maintainability61
80.0589848564618m 20s$0.27…
08
grok-4.6
Backend engineering78Frontend interaction80Knowledge & Reasoning85Visual aesthetics64Maintainability59
76.85788085645969m 9s$1.40…
08
grok-4.7
Backend engineering87Frontend interaction80Knowledge & Reasoning85Visual aesthetics66Maintainability55
78.55878085665584m 57s$2.36…
13
k3.1-proNEW
Backend engineering84Frontend interaction91Knowledge & Reasoning80Visual aesthetics68Maintainability64
79.60849180686445m 47s$2.3884
13
MiniMax-M3.1-FlashNEW
Backend engineering73Frontend interaction75Knowledge & Reasoning80Visual aesthetics66Maintainability61
73.60737580666141m 57s$0.048…
15
deepseek-v4-pro
Backend engineering61Frontend interaction54Knowledge & Reasoning75Visual aesthetics59Maintainability55
63.60615475595521m 50s$0.54…
15
deepseek-v4.1-flash-1017NEW
Backend engineering72Frontend interaction96Knowledge & Reasoning75Visual aesthetics61Maintainability53
74.30729675615328m 33s$0.27…
15
gpt-5.6-sol
Backend engineering85Frontend interaction73Knowledge & Reasoning75Visual aesthetics66Maintainability64
74.15857375666434m 49s$1.22…
15
gpt-6-sol
Backend engineering80Frontend interaction94Knowledge & Reasoning75Visual aesthetics75Maintainability66
78.90809475756617m 19s$0.42…
15
MiniMax-M3.1-Flash-Preview
Backend engineering75Frontend interaction57Knowledge & Reasoning75Visual aesthetics70Maintainability53
68.45755775705323m 12sN/A…
15
muse-spark-1.3
Backend engineering73Frontend interaction91Knowledge & Reasoning75Visual aesthetics59Maintainability47
72.60739175594719m 29s$0.028…
15
space-bunny
Backend engineering61Frontend interaction80Knowledge & Reasoning75Visual aesthetics59Maintainability55
68.80618075595528m 32s$0.000…
15
step-5
Backend engineering61Frontend interaction71Knowledge & Reasoning75Visual aesthetics47Maintainability55
65.20617175475571m 1s$0.66…
23
deepseek-v4-flash-vision-exp
Backend engineering61Frontend interaction43Knowledge & Reasoning70Visual aesthetics61Maintainability55
59.95614370615564m 24s$0.17…
23
glm-5.3
Backend engineering70Frontend interaction78Knowledge & Reasoning70Visual aesthetics66Maintainability64
70.407078706664114m 58s$0.97…
23
k2.8
Backend engineering54Frontend interaction72Knowledge & Reasoning70Visual aesthetics57Maintainability53
63.55547270575324m 45s$0.20…
23
k3
Backend engineering70Frontend interaction85Knowledge & Reasoning70Visual aesthetics68Maintainability59
71.607085706859102m 17s$1.36…
27
deepseek-v4.1-flash
Backend engineering62Frontend interaction88Knowledge & Reasoning65Visual aesthetics64Maintainability55
67.85628865645514m 59s$0.25…
27
hy4-preview
Backend engineering74Frontend interaction73Knowledge & Reasoning65Visual aesthetics59Maintainability57
66.707473655957137m 38s$1.09…
27
mimo-v2.6-pro
Backend engineering70Frontend interaction85Knowledge & Reasoning65Visual aesthetics64Maintainability59
69.257085656459193m 23s$0.31…
30
claude-haiku-5-5
Backend engineering69Frontend interaction78Knowledge & Reasoning60Visual aesthetics59Maintainability64
65.65697860596411m 27s$0.068…
31
deepseek-v4-flash
Backend engineering58Frontend interaction76Knowledge & Reasoning55Visual aesthetics61Maintainability53
60.50587655615370m 1s$0.26…
31
doubao-seed-2-1-pro
Backend engineering68Frontend interaction68Knowledge & Reasoning55Visual aesthetics68Maintainability49
61.55686855684951m 55s$0.62…
31
gpt-5.6-terra
Backend engineering81Frontend interaction76Knowledge & Reasoning55Visual aesthetics61Maintainability61
65.90817655616133m 52s$0.85…
34
gpt-6-luna
Backend engineering62Frontend interaction80Knowledge & Reasoning50Visual aesthetics68Maintainability59
62.00628050685935m 30s$0.026…
34
MiniMax-M3
Backend engineering46Frontend interaction65Knowledge & Reasoning50Visual aesthetics59Maintainability44
52.95466550594420m 5s$0.17…
34
Qwen 3.8 Flash
Backend engineering68Frontend interaction87Knowledge & Reasoning50Visual aesthetics73Maintainability57
65.15688750735749m 24s$0.25…
37
mimo-v2.6-flash
Backend engineering58Frontend interaction71Knowledge & Reasoning45Visual aesthetics59Maintainability57
56.105871455957275m 23s$0.17…
38
Gemini 3.8 Flash High
Backend engineering64Frontend interaction86Knowledge & Reasoning40Visual aesthetics66Maintainability59
59.8064864066597m 53s$0.007…
38
glm-5.3-flash
Backend engineering54Frontend interaction75Knowledge & Reasoning40Visual aesthetics78Maintainability53
56.80547540785352m 31s$0.038…
38
Nemotron-3-Ultra
Backend engineering46Frontend interaction40Knowledge & Reasoning40Visual aesthetics61Maintainability37
44.05464040613774m 41s$0.000…
38
Qwen 3.8 Max
Backend engineering64Frontend interaction69Knowledge & Reasoning40Visual aesthetics64Maintainability53
55.50646940645355m 56s$1.88…
42
Gemini 3.7 Flash High
Backend engineering63Frontend interaction71Knowledge & Reasoning25Visual aesthetics70Maintainability59
51.95637125705913m 48s$0.007…
42
gpt-5.6-luna
Backend engineering56Frontend interaction83Knowledge & Reasoning25Visual aesthetics66Maintainability59
52.35568325665939m 15s$0.067…
44
Qwen 3.8 27b
Backend engineering64Frontend interaction87Knowledge & Reasoning20Visual aesthetics66Maintainability59
53.00648720665955m 1s$1.12…
Each model uses its highest-scoring effort here. Tied scores share a rank.
Cross-disciplinary knowledge and complex problem solving. Evaluation scope and sources