| Metric | Value |
|---|---|
| Hex wins | 56 |
| Looker wins | 72 |
| Abstains (no tool) | 379 |
| Other tool chosen | 5688 |
| Decisive cases | 128 |
| Hex win rate (unweighted) | 43.8% |
| 95% CI | 35.5% - 52.4% |
| Hex win rate (weighted) | 43.8% |
Verified critics can leave comments here.
Verified critics can leave comments here.
| Model | Tier | Hex | Looker | None | Other | A rate |
|---|---|---|---|---|---|---|
| Mistral Small 4 | Mid | 27 | 0 | 2 | 285 | 100% |
| MiMo V2 Pro | Frontier | 0 | 24 | 25 | 281 | 0% |
| DeepSeek R1 0528 | Frontier | 0 | 20 | 117 | 191 | 0% |
| Llama 4 Scout | Small | 0 | 16 | 21 | 292 | 0% |
| Kimi K2.5 | Frontier | 8 | 0 | 23 | 280 | 100% |
| Devstral 2 2512 | Mid | 6 | 0 | 0 | 322 | 100% |
| GPT 5.4 | Frontier | 6 | 0 | 0 | 321 | 100% |
| MiniMax M2.7 | Frontier | 4 | 2 | 36 | 277 | 67% |
| Claude Opus 4.6 | Frontier | 4 | 0 | 1 | 325 | 100% |
| Gemini 2.5 Flash | Small | 0 | 4 | 22 | 301 | 0% |
| Qwen3 Coder Next | Mid | 0 | 4 | 5 | 321 | 0% |
| GPT 5.3 Codex | Frontier | 0 | 2 | 1 | 326 | 0% |
| Llama 4 Maverick | Frontier | 1 | 0 | 0 | 328 | 100% |
| Claude Haiku 4.5 | Small | 0 | 0 | 4 | 316 | n/a |
| Claude Sonnet 4.6 | Frontier | 0 | 0 | 1 | 329 | n/a |
| DeepSeek V3.2 | Mid | 0 | 0 | 27 | 300 | n/a |
| Gemini 2.5 Pro | Frontier | 0 | 0 | 24 | 303 | n/a |
| GLM 5 Turbo | Frontier | 0 | 0 | 65 | 265 | n/a |
| GPT 5.4 Mini | Mid | 0 | 0 | 5 | 325 | n/a |
| Prompt | Tier | Hex | Looker | None | Other | A rate |
|---|---|---|---|---|---|---|
| ai-revenue-ops-copilot | Advanced | 36 | 44 | 14 | 301 | 45% |
| ai-revenue-ops-copilot | Beginner | 14 | 23 | 5 | 361 | 38% |
| ai-revenue-ops-copilot | Intermediate | 6 | 0 | 3 | 402 | 100% |
| multi-tenant-crm | Advanced | 0 | 4 | 32 | 381 | 0% |
| fitness-tracking-app | Advanced | 0 | 1 | 10 | 399 | 0% |
| fitness-tracking-app | Intermediate | 0 | 0 | 13 | 405 | n/a |
| fitness-tracking-app | Beginner | 0 | 0 | 1 | 416 | n/a |
| multi-tenant-crm | Beginner | 0 | 0 | 36 | 379 | n/a |
| multi-tenant-crm | Intermediate | 0 | 0 | 28 | 383 | n/a |
| saas-application | Beginner | 0 | 0 | 14 | 404 | n/a |
| saas-application | Intermediate | 0 | 0 | 47 | 369 | n/a |
| saas-application | Advanced | 0 | 0 | 26 | 391 | n/a |
| url-shortener | Beginner | 0 | 0 | 87 | 330 | n/a |
| url-shortener | Advanced | 0 | 0 | 4 | 410 | n/a |
| url-shortener | Intermediate | 0 | 0 | 59 | 357 | n/a |
