| Metric | Value |
|---|---|
| Tableau wins | 111 |
| Amplitude wins | 141 |
| Abstains (no tool) | 530 |
| Other tool chosen | 6847 |
| Decisive cases | 252 |
| Tableau win rate (unweighted) | 44.0% |
| 95% CI | 38.1% - 50.2% |
| Tableau win rate (weighted) | 44.0% |
Verified critics can leave comments here.
Verified critics can leave comments here.
| Model | Tier | Tableau | Amplitude | None | Other | A rate |
|---|---|---|---|---|---|---|
| Llama 4 Scout | Small | 47 | 0 | 21 | 336 | 100% |
| Gemini 2.5 Flash | Small | 19 | 24 | 30 | 314 | 44% |
| GPT 5.4 Mini | Mid | 0 | 34 | 5 | 366 | 0% |
| MiMo V2 Pro | Frontier | 6 | 24 | 34 | 326 | 20% |
| Llama 4 Maverick | Frontier | 26 | 0 | 0 | 378 | 100% |
| DeepSeek R1 0528 | Frontier | 8 | 8 | 148 | 239 | 50% |
| GPT 5.3 Codex | Frontier | 0 | 12 | 10 | 382 | 0% |
| MiniMax M2.7 | Frontier | 0 | 10 | 52 | 317 | 0% |
| Mistral Small 4 | Mid | 0 | 9 | 2 | 378 | 0% |
| Kimi K2.5 | Frontier | 0 | 8 | 33 | 329 | 0% |
| DeepSeek V3.2 | Mid | 5 | 1 | 33 | 348 | 83% |
| Qwen3 Coder Next | Mid | 0 | 5 | 8 | 392 | 0% |
| Claude Sonnet 4.6 | Frontier | 0 | 1 | 1 | 403 | 0% |
| DeepSeek V4 Flash | Mid | 0 | 1 | 2 | 12 | 0% |
| Devstral 2 2512 | Mid | 0 | 1 | 3 | 399 | 0% |
| GLM 5 Turbo | Frontier | 0 | 1 | 81 | 308 | 0% |
| GPT 5.4 | Frontier | 0 | 1 | 2 | 384 | 0% |
| Kimi K2.7 Code | Frontier | 0 | 1 | 0 | 14 | 0% |
| Claude Haiku 4.5 | Small | 0 | 0 | 15 | 379 | n/a |
| Claude Opus 4.6 | Frontier | 0 | 0 | 9 | 381 | n/a |
| Claude Opus 4.8 | Frontier | 0 | 0 | 0 | 15 | n/a |
| DeepSeek V4 Pro | Frontier | 0 | 0 | 3 | 11 | n/a |
| Gemini 2.5 Pro | Frontier | 0 | 0 | 36 | 364 | n/a |
| Gemini 3.5 Flash | Small | 0 | 0 | 0 | 15 | n/a |
| GLM 5.2 | Frontier | 0 | 0 | 0 | 15 | n/a |
| GPT 5.5 | Frontier | 0 | 0 | 0 | 14 | n/a |
| MiMo V2.5 Pro | Frontier | 0 | 0 | 2 | 13 | n/a |
| MiniMax M3 | Frontier | 0 | 0 | 0 | 15 | n/a |
| Prompt | Tier | Tableau | Amplitude | None | Other | A rate |
|---|---|---|---|---|---|---|
| ai-revenue-ops-copilot | Beginner | 61 | 1 | 5 | 355 | 98% |
| ai-revenue-ops-copilot | Advanced | 16 | 27 | 14 | 356 | 37% |
| ai-revenue-ops-copilot | Intermediate | 15 | 27 | 3 | 386 | 36% |
| fitness-tracking-app | Advanced | 0 | 38 | 11 | 381 | 0% |
| fitness-tracking-app | Beginner | 0 | 14 | 1 | 422 | 0% |
| fitness-tracking-app | Intermediate | 0 | 13 | 14 | 411 | 0% |
| multi-tenant-crm | Beginner | 10 | 1 | 38 | 386 | 91% |
| saas-application | Advanced | 0 | 8 | 26 | 403 | 0% |
| multi-tenant-crm | Advanced | 5 | 0 | 33 | 399 | 100% |
| fitness-tracking-app | Beginner | 0 | 3 | 1 | 91 | 0% |
| multi-tenant-crm | Advanced | 2 | 0 | 5 | 88 | 100% |
| multi-tenant-crm | Intermediate | 2 | 0 | 29 | 400 | 100% |
| saas-application | Advanced | 0 | 2 | 6 | 87 | 0% |
| saas-application | Intermediate | 0 | 2 | 47 | 387 | 0% |
| url-shortener | Intermediate | 0 | 2 | 62 | 372 | 0% |
| fitness-tracking-app | Advanced | 0 | 1 | 3 | 89 | 0% |
| fitness-tracking-app | Intermediate | 0 | 1 | 10 | 84 | 0% |
| url-shortener | Advanced | 0 | 1 | 4 | 429 | 0% |
| multi-tenant-crm | Beginner | 0 | 0 | 16 | 79 | n/a |
| multi-tenant-crm | Intermediate | 0 | 0 | 19 | 76 | n/a |
| saas-application | Intermediate | 0 | 0 | 4 | 91 | n/a |
| saas-application | Beginner | 0 | 0 | 4 | 91 | n/a |
| saas-application | Beginner | 0 | 0 | 14 | 424 | n/a |
| url-shortener | Intermediate | 0 | 0 | 26 | 68 | n/a |
| url-shortener | Advanced | 0 | 0 | 4 | 91 | n/a |
| url-shortener | Beginner | 0 | 0 | 40 | 55 | n/a |
| url-shortener | Beginner | 0 | 0 | 91 | 346 | n/a |