| Metric | Value |
|---|---|
| Hex wins | 59 |
| Google BigQuery wins | 59 |
| Abstains (no tool) | 530 |
| Other tool chosen | 6981 |
| Decisive cases | 118 |
| Hex win rate (unweighted) | 50.0% |
| 95% CI | 41.1% - 58.9% |
| Hex win rate (weighted) | 50.0% |
Verified critics can leave comments here.
Verified critics can leave comments here.
| Model | Tier | Hex | Google BigQuery | None | Other | A rate |
|---|---|---|---|---|---|---|
| Mistral Small 4 | Mid | 28 | 0 | 2 | 359 | 100% |
| Llama 4 Maverick | Frontier | 1 | 18 | 0 | 385 | 5% |
| GPT 5.3 Codex | Frontier | 0 | 16 | 10 | 378 | 0% |
| Kimi K2.5 | Frontier | 8 | 0 | 33 | 329 | 100% |
| GPT 5.4 | Frontier | 6 | 2 | 2 | 377 | 75% |
| Devstral 2 2512 | Mid | 7 | 0 | 3 | 393 | 100% |
| DeepSeek R1 0528 | Frontier | 0 | 6 | 148 | 249 | 0% |
| Qwen3 Coder Next | Mid | 0 | 6 | 8 | 391 | 0% |
| Claude Opus 4.6 | Frontier | 4 | 0 | 9 | 377 | 100% |
| MiniMax M2.7 | Frontier | 4 | 0 | 52 | 323 | 100% |
| MiMo V2 Pro | Frontier | 0 | 4 | 34 | 352 | 0% |
| GPT 5.4 Mini | Mid | 0 | 3 | 5 | 397 | 0% |
| Gemini 2.5 Pro | Frontier | 0 | 2 | 36 | 362 | 0% |
| Claude Opus 4.8 | Frontier | 1 | 0 | 0 | 14 | 100% |
| GPT 5.5 | Frontier | 0 | 1 | 0 | 13 | 0% |
| MiMo V2.5 Pro | Frontier | 0 | 1 | 2 | 12 | 0% |
| Claude Haiku 4.5 | Small | 0 | 0 | 15 | 379 | n/a |
| Claude Sonnet 4.6 | Frontier | 0 | 0 | 1 | 404 | n/a |
| DeepSeek V3.2 | Mid | 0 | 0 | 33 | 354 | n/a |
| DeepSeek V4 Flash | Mid | 0 | 0 | 2 | 13 | n/a |
| DeepSeek V4 Pro | Frontier | 0 | 0 | 3 | 11 | n/a |
| Gemini 2.5 Flash | Small | 0 | 0 | 30 | 357 | n/a |
| Gemini 3.5 Flash | Small | 0 | 0 | 0 | 15 | n/a |
| GLM 5 Turbo | Frontier | 0 | 0 | 81 | 309 | n/a |
| GLM 5.2 | Frontier | 0 | 0 | 0 | 15 | n/a |
| Kimi K2.7 Code | Frontier | 0 | 0 | 0 | 15 | n/a |
| Llama 4 Scout | Small | 0 | 0 | 21 | 383 | n/a |
| MiniMax M3 | Frontier | 0 | 0 | 0 | 15 | n/a |
| Prompt | Tier | Hex | Google BigQuery | None | Other | A rate |
|---|---|---|---|---|---|---|
| ai-revenue-ops-copilot | Advanced | 37 | 7 | 14 | 355 | 84% |
| multi-tenant-crm | Advanced | 0 | 31 | 33 | 373 | 0% |
| ai-revenue-ops-copilot | Beginner | 15 | 0 | 5 | 402 | 100% |
| fitness-tracking-app | Advanced | 0 | 11 | 11 | 408 | 0% |
| ai-revenue-ops-copilot | Intermediate | 7 | 0 | 3 | 421 | 100% |
| url-shortener | Advanced | 0 | 6 | 4 | 424 | 0% |
| fitness-tracking-app | Advanced | 0 | 2 | 3 | 88 | 0% |
| multi-tenant-crm | Advanced | 0 | 2 | 5 | 88 | 0% |
| fitness-tracking-app | Intermediate | 0 | 0 | 10 | 85 | n/a |
| fitness-tracking-app | Beginner | 0 | 0 | 1 | 94 | n/a |
| fitness-tracking-app | Beginner | 0 | 0 | 1 | 436 | n/a |
| fitness-tracking-app | Intermediate | 0 | 0 | 14 | 424 | n/a |
| multi-tenant-crm | Beginner | 0 | 0 | 16 | 79 | n/a |
| multi-tenant-crm | Intermediate | 0 | 0 | 19 | 76 | n/a |
| multi-tenant-crm | Intermediate | 0 | 0 | 29 | 402 | n/a |
| multi-tenant-crm | Beginner | 0 | 0 | 38 | 397 | n/a |
| saas-application | Intermediate | 0 | 0 | 4 | 91 | n/a |
| saas-application | Advanced | 0 | 0 | 6 | 89 | n/a |
| saas-application | Beginner | 0 | 0 | 4 | 91 | n/a |
| saas-application | Intermediate | 0 | 0 | 47 | 389 | n/a |
| saas-application | Beginner | 0 | 0 | 14 | 424 | n/a |
| saas-application | Advanced | 0 | 0 | 26 | 411 | 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 | Intermediate | 0 | 0 | 62 | 374 | n/a |
| url-shortener | Beginner | 0 | 0 | 91 | 346 | n/a |