80.70Overall
Coding Rankings
Text Capability RankingsNEWCompare capability scores, evaluation time, and cost across models and reasoning efforts.
Evaluated on private datasetsMethodology
Data snapshot · 11/13/2026
93.00Overall
78.80Overall
About the scores
Interface behavior, interactions and state feedback. 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 methodScroll horizontally to view all scores and costs →
| Rank | Model | Eval. time | Speed tok/s | Actions | |||||||
|---|---|---|---|---|---|---|---|---|---|---|---|
| 01 | GPT-6.2 Astra Backend engineering94Frontend interaction98Knowledge & reasoning95Visual aesthetics80Maintainability75 | 92.05 | 94 | 98 | 95 | 80 | 75 | 7m 28s | N/A | 43 | |
| 02 | Claude Opus 5.5 Backend engineering81Frontend interaction97Knowledge & reasoning100Visual aesthetics73Maintainability70 | 89.75 | 81 | 97 | 100 | 73 | 70 | 48m 10s | $12.11 | … | |
| 03 | Claude Fable 5.2 Backend engineering97Frontend interaction96Knowledge & reasoning100Visual aesthetics83Maintainability73 | 94.00 | 97 | 96 | 100 | 83 | 73 | 104m 30s | $23.53 | … | |
| 03 | GPT-6 Astra Backend engineering92Frontend interaction96Knowledge & reasoning85Visual aesthetics70Maintainability70 | 86.15 | 92 | 96 | 85 | 70 | 70 | 21m 14s | $0.72 | … | |
| 03 | GPT-6.1 Sol Backend engineering95Frontend interaction96Knowledge & reasoning90Visual aesthetics66Maintainability70 | 88.10 | 95 | 96 | 90 | 66 | 70 | 24m 27s | $0.22 | … | |
| 06 | Gemini 4 Carbon Backend engineering90Frontend interaction95Knowledge & reasoning95Visual aesthetics78Maintainability68 | 89.60 | 90 | 95 | 95 | 78 | 68 | — | N/A | … | |
| 07 | GPT-6 Sol Backend engineering77Frontend interaction92Knowledge & reasoning75Visual aesthetics75Maintainability66 | 78.75 | 77 | 92 | 75 | 75 | 66 | 6m 50s | $0.22 | … | |
| 08 | Claude Fable 5.1 Backend engineering83Frontend interaction91Knowledge & reasoning95Visual aesthetics80Maintainability68 | 87.40 | 83 | 91 | 95 | 80 | 68 | 26m 10s | $6.68 | … | |
| 08 | DeepSeek V4.1 Flash (1017) Backend engineering69Frontend interaction91Knowledge & reasoning75Visual aesthetics61Maintainability53 | 74.20 | 69 | 91 | 75 | 61 | 53 | 21m 0s | $0.062 | … | |
| 08 | GPT-6.2 Sol Backend engineering96Frontend interaction91Knowledge & reasoning95Visual aesthetics73Maintainability64 | 88.90 | 96 | 91 | 95 | 73 | 64 | 16m 3s | N/A | … | |
| 08 | Kimi K3.1 Pro Backend engineering81Frontend interaction91Knowledge & reasoning80Visual aesthetics68Maintainability64 | 80.15 | 81 | 91 | 80 | 68 | 64 | 21m 13s | $0.75 | 84 | |
| 12 | Claude Opus 4.8 Backend engineering60Frontend interaction88Knowledge & reasoning85Visual aesthetics68Maintainability55 | 76.05 | 60 | 88 | 85 | 68 | 55 | 32m 18s | $4.18 | … | |
| 12 | GPT-5.6 Sol Backend engineering73Frontend interaction88Knowledge & reasoning65Visual aesthetics73Maintainability64 | 73.05 | 73 | 88 | 65 | 73 | 64 | 20m 30s | $0.28 | … | |
| 14 | Claude Sonnet 5.5 Backend engineering84Frontend interaction86Knowledge & reasoning85Visual aesthetics73Maintainability66 | 81.95 | 84 | 86 | 85 | 73 | 66 | 29m 45s | $1.17 | … | |
| 15 | Gemini 4 Hydrogen Backend engineering83Frontend interaction85Knowledge & reasoning85Visual aesthetics70Maintainability61 | 80.70 | 83 | 85 | 85 | 70 | 61 | 6m 4s | $0.64 | 91 | |
| 15 | Muse Spark 1.3 Backend engineering68Frontend interaction85Knowledge & reasoning75Visual aesthetics59Maintainability47 | 71.70 | 68 | 85 | 75 | 59 | 47 | 3m 18s | $0.014 | … | |
| 15 | Qwen3.8-27B Backend engineering59Frontend interaction85Knowledge & reasoning20Visual aesthetics66Maintainability59 | 52.55 | 59 | 85 | 20 | 66 | 59 | 26m 31s | $0.24 | … | |
| 18 | Gemini 3.8 Flash Backend engineering60Frontend interaction84Knowledge & reasoning40Visual aesthetics66Maintainability59 | 59.50 | 60 | 84 | 40 | 66 | 59 | 3m 52s | $0.062 | … | |
| 18 | GPT-6.1 Terra Backend engineering89Frontend interaction84Knowledge & reasoning85Visual aesthetics64Maintainability61 | 81.05 | 89 | 84 | 85 | 64 | 61 | 5m 13s | $0.20 | … | |
| 20 | Claude Opus 5 Backend engineering66Frontend interaction82Knowledge & reasoning95Visual aesthetics73Maintainability61 | 80.35 | 66 | 82 | 95 | 73 | 61 | 24m 45s | $3.20 | … | |
| 20 | Gemini 4 Argon Backend engineering79Frontend interaction82Knowledge & reasoning85Visual aesthetics70Maintainability59 | 78.95 | 79 | 82 | 85 | 70 | 59 | 19m 55s | N/A | … | |
| 20 | Kimi K3 Backend engineering65Frontend interaction82Knowledge & reasoning70Visual aesthetics68Maintainability59 | 70.70 | 65 | 82 | 70 | 68 | 59 | 18m 4s | $1.03 | … | |
| 23 | ![]() MiMo-V2.6-Pro Backend engineering66Frontend interaction81Knowledge & reasoning65Visual aesthetics64Maintainability59 | 68.50 | 66 | 81 | 65 | 64 | 59 | 62m 35s | $0.17 | … | |
| 23 | Muse Wonder Backend engineering72Frontend interaction81Knowledge & reasoning80Visual aesthetics73Maintainability57 | 75.65 | 72 | 81 | 80 | 73 | 57 | 3m 59s | $0.72 | … | |
| 25 | GLM-5.3 Backend engineering66Frontend interaction80Knowledge & reasoning50Visual aesthetics66Maintainability68 | 64.10 | 66 | 80 | 50 | 66 | 68 | 23m 23s | $0.43 | … | |
| 25 | MiniMax M3.1 Flash Backend engineering57Frontend interaction80Knowledge & reasoning65Visual aesthetics64Maintainability51 | 65.65 | 57 | 80 | 65 | 64 | 51 | 9m 41s | $0.024 | … | |
| 25 | QoDuck Backend engineering70Frontend interaction80Knowledge & reasoning85Visual aesthetics64Maintainability55 | 75.65 | 70 | 80 | 85 | 64 | 55 | 8m 20s | N/A | 95 | |
| 28 | DeepSeek V4.1 Flash (0910) Backend engineering57Frontend interaction78Knowledge & reasoning65Visual aesthetics64Maintainability55 | 65.55 | 57 | 78 | 65 | 64 | 55 | 8m 8s | $0.057 | … | |
| 28 | Egg Alpha Backend engineering65Frontend interaction78Knowledge & reasoning85Visual aesthetics61Maintainability51 | 73.45 | 65 | 78 | 85 | 61 | 51 | 5m 26s | N/A | 95 | |
| 28 | GPT-5.6 Luna Backend engineering54Frontend interaction78Knowledge & reasoning25Visual aesthetics66Maintainability59 | 51.55 | 54 | 78 | 25 | 66 | 59 | 12m 59s | $0.025 | … | |
| 28 | GPT-6 Luna Backend engineering57Frontend interaction78Knowledge & reasoning50Visual aesthetics68Maintainability59 | 61.10 | 57 | 78 | 50 | 68 | 59 | 10m 29s | $0.012 | … | |
| 28 | Qwen4-Max-Preview Backend engineering80Frontend interaction78Knowledge & reasoning90Visual aesthetics59Maintainability59 | 78.80 | 80 | 78 | 90 | 59 | 59 | 11m 28s | N/A | 84 | |
| 33 | HY4 Backend engineering90Frontend interaction77Knowledge & reasoning75Visual aesthetics59Maintainability64 | 75.80 | 90 | 77 | 75 | 59 | 64 | 43m 0s | N/A | … | |
| 34 | Claude Haiku 5.5 Backend engineering65Frontend interaction76Knowledge & reasoning60Visual aesthetics59Maintainability64 | 65.30 | 65 | 76 | 60 | 59 | 64 | 8m 0s | $0.066 | … | |
| 34 | GPT-5.6 Terra Backend engineering78Frontend interaction76Knowledge & reasoning55Visual aesthetics61Maintainability61 | 66.05 | 78 | 76 | 55 | 61 | 61 | 23m 25s | $0.38 | … | |
| 34 | Grok 4.6 Backend engineering75Frontend interaction76Knowledge & reasoning85Visual aesthetics64Maintainability59 | 76.05 | 75 | 76 | 85 | 64 | 59 | 31m 59s | $0.40 | … | |
| 37 | Grok 4.7 Backend engineering87Frontend interaction74Knowledge & reasoning85Visual aesthetics66Maintainability55 | 77.75 | 87 | 74 | 85 | 66 | 55 | 33m 52s | $0.89 | … | |
| 37 | Space Bunny Backend engineering57Frontend interaction74Knowledge & reasoning75Visual aesthetics59Maintainability55 | 67.55 | 57 | 74 | 75 | 59 | 55 | 14m 30s | $0.000 | … | |
| 39 | GLM-5.3-Flash Backend engineering52Frontend interaction71Knowledge & reasoning40Visual aesthetics70Maintainability53 | 54.45 | 52 | 71 | 40 | 70 | 53 | 26m 10s | $0.020 | … | |
| 40 | Qwen3.8-Flash Backend engineering59Frontend interaction70Knowledge & reasoning50Visual aesthetics55Maintainability66 | 58.90 | 59 | 70 | 50 | 55 | 66 | 29m 31s | $0.053 | 115 | |
| 41 | DeepSeek V4 Flash Backend engineering53Frontend interaction67Knowledge & reasoning55Visual aesthetics61Maintainability53 | 58.00 | 53 | 67 | 55 | 61 | 53 | 16m 48s | $0.067 | … | |
| 41 | Gemini 3.7 Flash Backend engineering59Frontend interaction67Knowledge & reasoning25Visual aesthetics70Maintainability59 | 50.20 | 59 | 67 | 25 | 70 | 59 | 4m 35s | $0.058 | … | |
| 41 | HY4 Preview Backend engineering69Frontend interaction67Knowledge & reasoning65Visual aesthetics59Maintainability57 | 64.90 | 69 | 67 | 65 | 59 | 57 | 13m 25s | $0.14 | … | |
| 41 | ![]() MiMo-V2.6-Flash Backend engineering54Frontend interaction67Knowledge & reasoning45Visual aesthetics59Maintainability57 | 54.90 | 54 | 67 | 45 | 59 | 57 | 75m 16s | $0.068 | … | |
| 41 | Qwen3.8-Max Backend engineering65Frontend interaction67Knowledge & reasoning65Visual aesthetics61Maintainability57 | 64.30 | 65 | 67 | 65 | 61 | 57 | 34m 33s | $0.49 | 59 | |
| 46 | Kimi K2.8 (Coding) Backend engineering55Frontend interaction65Knowledge & reasoning70Visual aesthetics57Maintainability53 | 62.75 | 55 | 65 | 70 | 57 | 53 | 23m 59s | $0.25 | … | |
| 47 | Crouton Alpha Backend engineering45Frontend interaction64Knowledge & reasoning45Visual aesthetics59Maintainability53 | 51.95 | 45 | 64 | 45 | 59 | 53 | 1m 20s | N/A | 553 | |
| 48 | LongCat-2.5 Backend engineering44Frontend interaction62Knowledge & reasoning75Visual aesthetics55Maintainability53 | 61.35 | 44 | 62 | 75 | 55 | 53 | 34m 13s | $0.26 | … | |
| 49 | Doubao Seed 2.1 Pro (260915) Backend engineering64Frontend interaction61Knowledge & reasoning55Visual aesthetics68Maintainability49 | 59.00 | 64 | 61 | 55 | 68 | 49 | 33m 16s | $0.32 | … | |
| 49 | ![]() Step-5 Preview Backend engineering56Frontend interaction61Knowledge & reasoning75Visual aesthetics47Maintainability55 | 62.90 | 56 | 61 | 75 | 47 | 55 | 20m 9s | $0.24 | … | |
| 51 | DeepSeek V4 Pro Backend engineering64Frontend interaction60Knowledge & reasoning65Visual aesthetics70Maintainability59 | 63.45 | 64 | 60 | 65 | 70 | 59 | 18m 41s | $0.16 | … | |
| 52 | MiniMax M3 Backend engineering43Frontend interaction59Knowledge & reasoning50Visual aesthetics59Maintainability44 | 51.15 | 43 | 59 | 50 | 59 | 44 | 14m 22s | $0.14 | … | |
| 53 | Ling-3.2-Flash Backend engineering59Frontend interaction54Knowledge & reasoning60Visual aesthetics61Maintainability57 | 58.10 | 59 | 54 | 60 | 61 | 57 | 28m 24s | N/A | … | |
| 54 | MiniMax M3.1 Flash Preview Backend engineering71Frontend interaction53Knowledge & reasoning75Visual aesthetics70Maintainability53 | 66.00 | 71 | 53 | 75 | 70 | 53 | 12m 20s | N/A | … | |
| 55 | ERNIE 5.5 Flash Preview Backend engineering52Frontend interaction52Knowledge & reasoning90Visual aesthetics66Maintainability57 | 67.20 | 52 | 52 | 90 | 66 | 57 | 8m 11s | $0.10 | 80 | |
| 56 | DeepSeek V4 Flash Vision Exp Backend engineering57Frontend interaction39Knowledge & reasoning70Visual aesthetics61Maintainability55 | 57.25 | 57 | 39 | 70 | 61 | 55 | 11m 8s | $0.045 | … | |
| 57 | NVIDIA Nemotron 3 Ultra (550B-A55B) Backend engineering42Frontend interaction34Knowledge & reasoning40Visual aesthetics61Maintainability37 | 40.70 | 42 | 34 | 40 | 61 | 37 | 17m 46s | $0.000 | … |
Each model uses its highest-scoring effort here. Tied scores share a rank.
Evaluation methodology
Interface behavior, interactions and state feedback.

