Society
Tested
- Avg AIMAC Debt 6.23
- Avg Cost $0.19
- Models Tested 42
- Zero Debt 4
- Avg Violations 13.1
Insights for Society
- Common Issues: Elements must meet minimum color contrast ratio thresholds, Links must have discernible text, Select element must have an accessible name
- Category Difficulty: Rank #22 of 28 categories (based on average model performance)
- Real-World Comparison: The WebAIM Million audits accessibility across 1 million real websites annually. Using different automated tools, AI models showed 77.7% fewer detected issues than real Society websites (13.1 axe-core violations vs 59.0 WAVE errors).
Model Gallery
Click a screenshot to view the generated HTML page, or click the model name for detailed results and prompts.
Model Results
AIMAC Debt:The model's accessibility debt for this category (lower = better)
| lower = better | in usd | |||
|---|---|---|---|---|
| GPT 5.1 Codex Mini | 0.00 | $0.014 | 0 | 0 |
| GLM 5 | 0.00 | $0.06 | 0 | 0 |
| GPT 5.4 | 0.00 | $0.14 | 0 | 0 |
| GPT 5.4 Mini | 0.00 | $0.03 | 0 | 0 |
| Trinity Large Preview (free) | 2.00 | $0.00 | 0 | 1 |
| Olmo 3.1 32B Instruct | 2.00 | $0.0045 | 0 | 1 |
| Qwen3.6 Plus Preview (free) | 2.66 | $0.00 | 0 | 2 |
| DeepSeek V3.2 Speciale | 3.05 | $0.007 | 0 | 3 |
| GPT 5.3 Codex | 3.05 | $0.12 | 0 | 3 |
| GPT 5.4 Pro | 3.32 | $5.78 | 0 | 4 |
| Trinity Large Thinking | 3.32 | $0.009 | 0 | 4 |
| Gemini 3.1 Pro Preview | 3.85 | $0.12 | 0 | 7 |
| o4 Mini | 3.98 | $0.018 | 0 | 8 |
| Qwen3 Max | 4.00 | $0.034 | 0 | 4 |
| Qwen3.5 397B A17B | 4.19 | $0.03 | 0 | 10 |
| Claude Opus 4.6 | 4.28 | $0.54 | 0 | 11 |
| Qwen3.5 Flash | 4.28 | $0.0035 | 0 | 11 |
| gpt oss 120b | 4.51 | $0.004 | 0 | 14 |
| MiniMax M2.7 | 4.64 | $0.036 | 0 | 16 |
| Claude Haiku 4.5 | 4.75 | $0.08 | 0 | 18 |
| Nova 2 Lite | 4.75 | $0.012 | 0 | 18 |
| Grok 4.20 | 4.75 | $0.07 | 0 | 18 |
| Grok 4.1 Fast | 5.10 | $0.003 | 0 | 26 |
| Mistral Medium 3.1 | 5.10 | $0.014 | 0 | 26 |
| Nemotron 3 Super (free) | 5.41 | $0.00 | 0 | 36 |
| Kimi K2 Thinking | 5.54 | $0.025 | 0 | 41 |
| Gemini 3 Flash Preview | 6.63 | $0.04 | 0 | 6 |
| KAT Coder Pro V2 | 7.09 | $0.014 | 0 | 11 |
| Qwen3 Coder Next | 7.28 | $0.01 | 0 | 13 |
| Devstral 2 2512 | 7.68 | $0.005 | 0 | 12 |
| Qwen3 Max Thinking | 7.85 | $0.036 | 0 | 10 |
| Qwen3 Coder Flash | 8.09 | $0.01 | 0 | 13 |
| GLM 4.7 Flash | 8.09 | $0.004 | 0 | 13 |
| o3 | 8.37 | $0.04 | 0 | 16 |
| Mistral Large 3 2512 | 8.44 | $0.018 | 0 | 17 |
| Kimi K2.5 | 9.90 | $0.03 | 1 | 21 |
| DeepSeek V3.2 | 9.91 | $0.0034 | 0 | 9 |
| R1 0528 | 10.03 | $0.02 | 0 | 12 |
| Qwen3 Coder Plus | 13.75 | $0.015 | 3 | 0 |
| Claude Sonnet 4.6 | 18.01 | $0.42 | 4 | 40 |
| Mistral Small 4 | 19.64 | $0.005 | 3 | 21 |
| Codestral 2508 | 22.38 | $0.005 | 3 | 42 |