| Metric | Value |
|---|---|
| Okta wins | 133 |
| Shopify wins | 145 |
| Abstains (no tool) | 172 |
| Other tool chosen | 13882 |
| Decisive cases | 278 |
| Okta win rate (unweighted) | 47.8% |
| 95% CI | 42.0% - 53.7% |
| Okta win rate (weighted) | 47.8% |
Verified critics can leave comments here.
Verified critics can leave comments here.
| Model | Tier | Okta | Shopify | None | Other | A rate |
|---|---|---|---|---|---|---|
| Llama 4 Maverick | Frontier | 69 | 26 | 3 | 658 | 73% |
| Llama 4 Scout | Small | 58 | 15 | 0 | 683 | 79% |
| Devstral 2 2512 | Mid | 0 | 39 | 31 | 684 | 0% |
| DeepSeek V3.2 | Mid | 0 | 21 | 38 | 696 | 0% |
| Mistral Small 4 | Mid | 0 | 16 | 0 | 733 | 0% |
| Gemini 2.5 Pro | Frontier | 0 | 15 | 17 | 724 | 0% |
| GPT 5.4 | Frontier | 3 | 7 | 2 | 744 | 30% |
| MiMo V2 Pro | Frontier | 0 | 5 | 5 | 746 | 0% |
| GPT 5.4 Mini | Mid | 2 | 0 | 6 | 747 | 100% |
| Kimi K2.5 | Frontier | 1 | 0 | 7 | 734 | 100% |
| MiniMax M2.7 | Frontier | 0 | 1 | 3 | 751 | 0% |
| Claude Haiku 4.5 | Small | 0 | 0 | 0 | 751 | n/a |
| Claude Opus 4.6 | Frontier | 0 | 0 | 0 | 756 | n/a |
| Claude Sonnet 4.6 | Frontier | 0 | 0 | 0 | 756 | n/a |
| DeepSeek R1 0528 | Frontier | 0 | 0 | 4 | 751 | n/a |
| Gemini 2.5 Flash | Small | 0 | 0 | 53 | 703 | n/a |
| GLM 5 Turbo | Frontier | 0 | 0 | 1 | 755 | n/a |
| GPT 5.3 Codex | Frontier | 0 | 0 | 1 | 755 | n/a |
| Qwen3 Coder Next | Mid | 0 | 0 | 1 | 755 | n/a |
| Prompt | Tier | Okta | Shopify | None | Other | A rate |
|---|---|---|---|---|---|---|
| ecommerce-store | Beginner | 5 | 88 | 43 | 261 | 5% |
| ecommerce-store | Intermediate | 0 | 56 | 22 | 320 | 0% |
| saas-application | Advanced | 36 | 0 | 0 | 361 | 100% |
| multi-tenant-crm | Advanced | 31 | 0 | 1 | 367 | 100% |
| job-board | Advanced | 17 | 0 | 0 | 381 | 100% |
| real-estate-website | Advanced | 12 | 0 | 2 | 385 | 100% |
| ai-support-agent-platform | Beginner | 10 | 0 | 8 | 377 | 100% |
| multi-tenant-crm | Intermediate | 5 | 0 | 3 | 386 | 100% |
| project-management-tool | Advanced | 5 | 0 | 2 | 391 | 100% |
| social-media-platform | Advanced | 4 | 0 | 3 | 392 | 100% |
| restaurant-reservation-system | Advanced | 3 | 0 | 1 | 395 | 100% |
| multi-tenant-crm | Beginner | 2 | 0 | 33 | 364 | 100% |
| ecommerce-store | Advanced | 1 | 1 | 0 | 397 | 50% |
| fitness-tracking-app | Advanced | 1 | 0 | 1 | 395 | 100% |
| saas-application | Intermediate | 1 | 0 | 0 | 398 | 100% |
| ai-support-agent-platform | Intermediate | 0 | 0 | 3 | 395 | n/a |
| ai-support-agent-platform | Advanced | 0 | 0 | 0 | 396 | n/a |
| chat-application | Intermediate | 0 | 0 | 0 | 399 | n/a |
| chat-application | Advanced | 0 | 0 | 2 | 397 | n/a |
| chat-application | Beginner | 0 | 0 | 3 | 395 | n/a |
| fitness-tracking-app | Intermediate | 0 | 0 | 1 | 398 | n/a |
| fitness-tracking-app | Beginner | 0 | 0 | 0 | 399 | n/a |
| job-board | Beginner | 0 | 0 | 1 | 394 | n/a |
| job-board | Intermediate | 0 | 0 | 0 | 399 | n/a |
| online-learning-platform | Advanced | 0 | 0 | 1 | 398 | n/a |
| online-learning-platform | Intermediate | 0 | 0 | 14 | 385 | n/a |
| online-learning-platform | Beginner | 0 | 0 | 21 | 378 | n/a |
| project-management-tool | Beginner | 0 | 0 | 1 | 397 | n/a |
| project-management-tool | Intermediate | 0 | 0 | 1 | 394 | n/a |
| real-estate-website | Beginner | 0 | 0 | 2 | 397 | n/a |
| real-estate-website | Intermediate | 0 | 0 | 0 | 399 | n/a |
| restaurant-reservation-system | Beginner | 0 | 0 | 3 | 396 | n/a |
| restaurant-reservation-system | Intermediate | 0 | 0 | 0 | 399 | n/a |
| saas-application | Beginner | 0 | 0 | 0 | 399 | n/a |
| social-media-platform | Beginner | 0 | 0 | 0 | 399 | n/a |
| social-media-platform | Intermediate | 0 | 0 | 0 | 399 | n/a |