| Metric | Value |
|---|---|
| Tableau wins | 126 |
| Plausible wins | 145 |
| Abstains (no tool) | 459 |
| Other tool chosen | 7235 |
| Decisive cases | 271 |
| Tableau win rate (unweighted) | 46.5% |
| 95% CI | 40.6% - 52.4% |
| Tableau win rate (weighted) | 46.5% |
Verified critics can leave comments here.
Verified critics can leave comments here.
| Model | Tier | Tableau | Plausible | None | Other | A rate |
|---|---|---|---|---|---|---|
| Llama 4 Scout | Small | 56 | 13 | 25 | 324 | 81% |
| DeepSeek V3.2 | Mid | 5 | 48 | 27 | 247 | 9% |
| Llama 4 Maverick | Frontier | 31 | 3 | 0 | 385 | 91% |
| Claude Haiku 4.5 | Small | 0 | 27 | 5 | 374 | 0% |
| Gemini 2.5 Flash | Small | 19 | 0 | 22 | 286 | 100% |
| DeepSeek R1 0528 | Frontier | 9 | 10 | 149 | 250 | 47% |
| Claude Opus 4.6 | Frontier | 0 | 11 | 1 | 318 | 0% |
| MiMo V2 Pro | Frontier | 6 | 4 | 25 | 295 | 60% |
| Qwen3 Coder Next | Mid | 0 | 10 | 5 | 405 | 0% |
| GPT 5.4 | Frontier | 0 | 9 | 0 | 318 | 0% |
| DeepSeek V4 Flash | Mid | 0 | 4 | 4 | 80 | 0% |
| Kimi K2.7 Code | Frontier | 0 | 2 | 3 | 85 | 0% |
| MiniMax M2.7 | Frontier | 0 | 2 | 36 | 281 | 0% |
| DeepSeek V4 Pro | Frontier | 0 | 1 | 15 | 73 | 0% |
| Devstral 2 2512 | Mid | 0 | 1 | 0 | 402 | 0% |
| Claude Opus 4.8 | Frontier | 0 | 0 | 0 | 89 | n/a |
| Claude Sonnet 4.6 | Frontier | 0 | 0 | 1 | 419 | n/a |
| Gemini 2.5 Pro | Frontier | 0 | 0 | 26 | 390 | n/a |
| Gemini 3.5 Flash | Small | 0 | 0 | 0 | 90 | n/a |
| GLM 5 Turbo | Frontier | 0 | 0 | 65 | 265 | n/a |
| GLM 5.2 | Frontier | 0 | 0 | 1 | 89 | n/a |
| GPT 5.3 Codex | Frontier | 0 | 0 | 1 | 418 | n/a |
| GPT 5.4 Mini | Mid | 0 | 0 | 7 | 412 | n/a |
| GPT 5.5 | Frontier | 0 | 0 | 1 | 86 | n/a |
| Kimi K2.5 | Frontier | 0 | 0 | 23 | 288 | n/a |
| MiMo V2.5 Pro | Frontier | 0 | 0 | 11 | 79 | n/a |
| MiniMax M3 | Frontier | 0 | 0 | 3 | 87 | n/a |
| Mistral Small 4 | Mid | 0 | 0 | 3 | 400 | n/a |
| Prompt | Tier | Tableau | Plausible | None | Other | A rate |
|---|---|---|---|---|---|---|
| url-shortener | Beginner | 0 | 83 | 109 | 344 | 0% |
| ai-revenue-ops-copilot | Beginner | 70 | 0 | 5 | 445 | 100% |
| url-shortener | Intermediate | 0 | 43 | 75 | 417 | 0% |
| ai-revenue-ops-copilot | Intermediate | 18 | 0 | 3 | 508 | 100% |
| ai-revenue-ops-copilot | Advanced | 17 | 0 | 16 | 473 | 100% |
| multi-tenant-crm | Beginner | 10 | 0 | 47 | 477 | 100% |
| multi-tenant-crm | Advanced | 9 | 0 | 37 | 490 | 100% |
| fitness-tracking-app | Beginner | 0 | 7 | 1 | 528 | 0% |
| saas-application | Beginner | 0 | 7 | 16 | 514 | 0% |
| multi-tenant-crm | Intermediate | 2 | 1 | 34 | 493 | 67% |
| url-shortener | Advanced | 0 | 2 | 5 | 525 | 0% |
| fitness-tracking-app | Intermediate | 0 | 1 | 16 | 520 | 0% |
| saas-application | Intermediate | 0 | 1 | 52 | 482 | 0% |
| fitness-tracking-app | Advanced | 0 | 0 | 13 | 513 | n/a |
| saas-application | Advanced | 0 | 0 | 30 | 506 | n/a |