80.05Overall
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
79.60Overall
73.60Overall
About the scores
Interface behavior, user interactions, and state feedback. 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 methodScroll horizontally to view all scores and costs →
| Rank | Model | Eval. time | Speed tok/s | Actions | |||||||
|---|---|---|---|---|---|---|---|---|---|---|---|
| 01 |  claude-opus-5-5 Backend engineering84Frontend interaction97Knowledge & Reasoning100Visual aesthetics73Maintainability70 | 89.15 | 84 | 97 | 100 | 73 | 70 | 48m 10s | $12.11 | … | |
| 02 |  deepseek-v4.1-flash-1017 Backend engineering72Frontend interaction96Knowledge & Reasoning75Visual aesthetics61Maintainability53 | 74.30 | 72 | 96 | 75 | 61 | 53 | 21m 0s | $0.062 | … | |
| 02 |  gpt-6-astra Backend engineering95Frontend interaction96Knowledge & Reasoning95Visual aesthetics75Maintainability61 | 88.80 | 95 | 96 | 95 | 75 | 61 | 16m 21s | $1.51 | … | |
| 02 | gpt-6.1-sol Backend engineering95Frontend interaction96Knowledge & Reasoning90Visual aesthetics66Maintainability70 | 86.60 | 95 | 96 | 90 | 66 | 70 | 24m 27s | $0.22 | … | |
| 05 | gpt-6-sol Backend engineering80Frontend interaction94Knowledge & Reasoning75Visual aesthetics75Maintainability66 | 78.90 | 80 | 94 | 75 | 75 | 66 | 6m 50s | $0.22 | … | |
| 06 | claude-fable-5-1 Backend engineering85Frontend interaction91Knowledge & Reasoning95Visual aesthetics80Maintainability68 | 87.25 | 85 | 91 | 95 | 80 | 68 | 26m 10s | $6.68 | … | |
| 06 |  k3.1-pro Backend engineering84Frontend interaction91Knowledge & Reasoning80Visual aesthetics68Maintainability64 | 79.60 | 84 | 91 | 80 | 68 | 64 | 21m 13s | $0.75 | 84 | |
| 06 |  muse-spark-1.3 Backend engineering73Frontend interaction91Knowledge & Reasoning75Visual aesthetics59Maintainability47 | 72.60 | 73 | 91 | 75 | 59 | 47 | 3m 18s | $0.014 | … | |
| 09 | gpt-5.6-sol Backend engineering78Frontend interaction90Knowledge & Reasoning65Visual aesthetics73Maintainability64 | 73.70 | 78 | 90 | 65 | 73 | 64 | 20m 30s | $0.28 | … | |
| 10 | claude-sonnet-5-5 Backend engineering86Frontend interaction89Knowledge & Reasoning85Visual aesthetics73Maintainability66 | 82.30 | 86 | 89 | 85 | 73 | 66 | 29m 45s | $1.17 | … | |
| 11 | claude-opus-4-8 Backend engineering64Frontend interaction88Knowledge & Reasoning85Visual aesthetics68Maintainability55 | 75.85 | 64 | 88 | 85 | 68 | 55 | 32m 18s | $4.18 | … | |
| 11 | deepseek-v4.1-flash Backend engineering62Frontend interaction88Knowledge & Reasoning65Visual aesthetics64Maintainability55 | 67.85 | 62 | 88 | 65 | 64 | 55 | 8m 8s | $0.057 | … | |
| 11 |  MiniMax-M3.1-Flash Backend engineering62Frontend interaction88Knowledge & Reasoning65Visual aesthetics64Maintainability51 | 67.45 | 62 | 88 | 65 | 64 | 51 | 9m 41s | $0.024 | … | |
| 14 | claude-opus-5 Backend engineering70Frontend interaction87Knowledge & Reasoning95Visual aesthetics73Maintainability61 | 81.70 | 70 | 87 | 95 | 73 | 61 | 24m 45s | $3.20 | … | |
| 14 |  Qwen 3.8 27b Backend engineering64Frontend interaction87Knowledge & Reasoning20Visual aesthetics66Maintainability59 | 53.00 | 64 | 87 | 20 | 66 | 59 | 26m 31s | $0.24 | … | |
| 14 | Qwen 3.8 Flash Backend engineering68Frontend interaction87Knowledge & Reasoning50Visual aesthetics73Maintainability57 | 65.15 | 68 | 87 | 50 | 73 | 57 | 29m 54s | $0.050 | … | |
| 17 |  Gemini 3.8 Flash High Backend engineering64Frontend interaction86Knowledge & Reasoning40Visual aesthetics66Maintainability59 | 59.80 | 64 | 86 | 40 | 66 | 59 | 3m 52s | $0.062 | … | |
| 18 | gpt-6.1-terra Backend engineering55Frontend interaction85Knowledge & Reasoning75Visual aesthetics47Maintainability59 | 67.20 | 55 | 85 | 75 | 47 | 59 | 1m 2s | $0.072 | … | |
| 18 | k3 Backend engineering70Frontend interaction85Knowledge & Reasoning70Visual aesthetics68Maintainability59 | 71.60 | 70 | 85 | 70 | 68 | 59 | 18m 4s | $1.03 | … | |
| 18 |  mimo-v2.6-pro Backend engineering70Frontend interaction85Knowledge & Reasoning65Visual aesthetics64Maintainability59 | 69.25 | 70 | 85 | 65 | 64 | 59 | 62m 35s | $0.17 | … | |
| 18 | muse-wonder Backend engineering77Frontend interaction85Knowledge & Reasoning80Visual aesthetics73Maintainability57 | 77.05 | 77 | 85 | 80 | 73 | 57 | 3m 59s | $0.72 | … | |
| 22 | Gemini 4 Argon Backend engineering82Frontend interaction84Knowledge & Reasoning85Visual aesthetics70Maintainability59 | 79.35 | 82 | 84 | 85 | 70 | 59 | 19m 55s | N/A | … | |
Gemini 4 Argon · Test resultsTime and reference cost correspond to Frontend interaction tasks. Tested effortOverallBackend engineeringFrontend interactionKnowledge & ReasoningVisual aestheticsMaintainabilityEvaluation timeReference costSpeed tok/sCompare highShown in ranking 19m 55sN/A…Scroll horizontally to view all scores and costs → Score breakdown
Interface behavior, user interactions, and state feedback. Layout and adaptation17 / 20 Content organization, layout constraints, and responsive adaptation. Interaction behavior20 / 20 Input response, completed workflows, and edge-case interactions. State continuity20 / 20 State propagation, recovery, and continuity across actions. Accessibility and feedback12 / 15 Control semantics, accessibility support, and clear feedback. State validation and regression15 / 25 Expected-state verification and behavioral regression checks. | |||||||||||
| 23 | gpt-5.6-luna Backend engineering56Frontend interaction83Knowledge & Reasoning25Visual aesthetics66Maintainability59 | 52.35 | 56 | 83 | 25 | 66 | 59 | 12m 59s | $0.025 | … | |
| 24 |  glm-5.3 Backend engineering69Frontend interaction82Knowledge & Reasoning50Visual aesthetics66Maintainability68 | 64.40 | 69 | 82 | 50 | 66 | 68 | 23m 23s | $0.43 | … | |
| 25 | gpt-6-luna Backend engineering62Frontend interaction80Knowledge & Reasoning50Visual aesthetics68Maintainability59 | 62.00 | 62 | 80 | 50 | 68 | 59 | 10m 29s | $0.012 | … | |
| 25 |  grok-4.6 Backend engineering78Frontend interaction80Knowledge & Reasoning85Visual aesthetics64Maintainability59 | 76.85 | 78 | 80 | 85 | 64 | 59 | 31m 59s | $0.40 | … | |
| 25 | grok-4.7 Backend engineering87Frontend interaction80Knowledge & Reasoning85Visual aesthetics66Maintainability55 | 78.55 | 87 | 80 | 85 | 66 | 55 | 33m 52s | $0.89 | … | |
| 25 |  space-bunny Backend engineering61Frontend interaction80Knowledge & Reasoning75Visual aesthetics59Maintainability55 | 68.80 | 61 | 80 | 75 | 59 | 55 | 14m 30s | $0.000 | … | |
| 29 | claude-haiku-5-5 Backend engineering69Frontend interaction78Knowledge & Reasoning60Visual aesthetics59Maintainability64 | 65.65 | 69 | 78 | 60 | 59 | 64 | 8m 0s | $0.066 | … | |
| 30 | deepseek-v4-flash Backend engineering58Frontend interaction76Knowledge & Reasoning55Visual aesthetics61Maintainability53 | 60.50 | 58 | 76 | 55 | 61 | 53 | 16m 48s | $0.067 | … | |
| 30 | glm-5.3-flash Backend engineering55Frontend interaction76Knowledge & Reasoning20Visual aesthetics70Maintainability59 | 49.60 | 55 | 76 | 20 | 70 | 59 | 29m 43s | $0.025 | … | |
| 30 | gpt-5.6-terra Backend engineering81Frontend interaction76Knowledge & Reasoning55Visual aesthetics61Maintainability61 | 65.90 | 81 | 76 | 55 | 61 | 61 | 23m 25s | $0.38 | … | |
| 33 |  hy4-preview Backend engineering74Frontend interaction73Knowledge & Reasoning65Visual aesthetics59Maintainability57 | 66.70 | 74 | 73 | 65 | 59 | 57 | 13m 25s | $0.14 | … | |
| 34 | k2.8 Backend engineering54Frontend interaction72Knowledge & Reasoning70Visual aesthetics57Maintainability53 | 63.55 | 54 | 72 | 70 | 57 | 53 | 23m 59s | $0.25 | … | |
| 35 | Gemini 3.7 Flash High Backend engineering63Frontend interaction71Knowledge & Reasoning25Visual aesthetics70Maintainability59 | 51.95 | 63 | 71 | 25 | 70 | 59 | 4m 35s | $0.058 | … | |
| 35 | mimo-v2.6-flash Backend engineering58Frontend interaction71Knowledge & Reasoning45Visual aesthetics59Maintainability57 | 56.10 | 58 | 71 | 45 | 59 | 57 | 75m 16s | $0.068 | … | |
| 35 |  step-5 Backend engineering61Frontend interaction71Knowledge & Reasoning75Visual aesthetics47Maintainability55 | 65.20 | 61 | 71 | 75 | 47 | 55 | 20m 9s | $0.24 | … | |
| 38 | Qwen 3.8 Max Backend engineering64Frontend interaction69Knowledge & Reasoning40Visual aesthetics64Maintainability53 | 55.50 | 64 | 69 | 40 | 64 | 53 | 29m 19s | $0.46 | … | |
| 39 |  doubao-seed-2-1-pro Backend engineering68Frontend interaction68Knowledge & Reasoning55Visual aesthetics68Maintainability49 | 61.55 | 68 | 68 | 55 | 68 | 49 | 33m 16s | $0.32 | … | |
| 40 | MiniMax-M3 Backend engineering46Frontend interaction65Knowledge & Reasoning50Visual aesthetics59Maintainability44 | 52.95 | 46 | 65 | 50 | 59 | 44 | 14m 22s | $0.14 | … | |
| 41 | deepseek-v4-pro Backend engineering67Frontend interaction63Knowledge & Reasoning65Visual aesthetics70Maintainability59 | 65.15 | 67 | 63 | 65 | 70 | 59 | 18m 41s | $0.16 | … | |
| 42 | MiniMax-M3.1-Flash-Preview Backend engineering75Frontend interaction57Knowledge & Reasoning75Visual aesthetics70Maintainability53 | 68.45 | 75 | 57 | 75 | 70 | 53 | 12m 20s | N/A | … | |
| 43 | deepseek-v4-flash-vision-exp Backend engineering61Frontend interaction43Knowledge & Reasoning70Visual aesthetics61Maintainability55 | 59.95 | 61 | 43 | 70 | 61 | 55 | 11m 8s | $0.045 | … | |
| 44 |  Nemotron-3-Ultra Backend engineering46Frontend interaction40Knowledge & Reasoning40Visual aesthetics61Maintainability37 | 44.05 | 46 | 40 | 40 | 61 | 37 | 17m 46s | $0.000 | … | |
Each model uses its highest-scoring effort here. Tied scores share a rank.
Interface behavior, user interactions, and state feedback. Evaluation scope and sources