| Metric | Value |
|---|---|
| Hex wins | 69 |
| Google BigQuery wins | 73 |
| Abstains (no tool) | 460 |
| Other tool chosen | 7365 |
| Decisive cases | 142 |
| Hex win rate (unweighted) | 48.6% |
| 95% CI | 40.5% - 56.7% |
| Hex win rate (weighted) | 48.6% |
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 | 36 | 0 | 3 | 363 | 100% |
| Llama 4 Maverick | Frontier | 1 | 22 | 0 | 396 | 4% |
| GPT 5.3 Codex | Frontier | 0 | 20 | 1 | 398 | 0% |
| Devstral 2 2512 | Mid | 9 | 0 | 0 | 379 | 100% |
| Kimi K2.5 | Frontier | 8 | 0 | 23 | 269 | 100% |
| DeepSeek R1 0528 | Frontier | 0 | 8 | 150 | 260 | 0% |
| GPT 5.4 | Frontier | 6 | 1 | 0 | 305 | 86% |
| Qwen3 Coder Next | Mid | 0 | 7 | 5 | 407 | 0% |
| Claude Opus 4.6 | Frontier | 4 | 0 | 1 | 310 | 100% |
| GPT 5.4 Mini | Mid | 0 | 4 | 7 | 408 | 0% |
| GPT 5.5 | Frontier | 0 | 4 | 2 | 95 | 0% |
| MiMo V2 Pro | Frontier | 0 | 3 | 24 | 288 | 0% |
| MiniMax M2.7 | Frontier | 2 | 0 | 36 | 266 | 100% |
| Gemini 2.5 Pro | Frontier | 0 | 2 | 23 | 391 | 0% |
| MiMo V2.5 Pro | Frontier | 0 | 2 | 13 | 90 | 0% |
| Claude Opus 4.8 | Frontier | 1 | 0 | 0 | 103 | 100% |
| DeepSeek V4 Pro | Frontier | 1 | 0 | 18 | 85 | 100% |
| Kimi K2.7 Code | Frontier | 1 | 0 | 3 | 101 | 100% |
| Claude Haiku 4.5 | Small | 0 | 0 | 6 | 401 | n/a |
| Claude Sonnet 4.6 | Frontier | 0 | 0 | 1 | 419 | n/a |
| DeepSeek V3.2 | Mid | 0 | 0 | 26 | 286 | n/a |
| DeepSeek V4 Flash | Mid | 0 | 0 | 5 | 98 | n/a |
| Gemini 2.5 Flash | Small | 0 | 0 | 21 | 291 | n/a |
| Gemini 3.5 Flash | Small | 0 | 0 | 0 | 105 | n/a |
| GLM 5 Turbo | Frontier | 0 | 0 | 63 | 252 | n/a |
| GLM 5.2 | Frontier | 0 | 0 | 1 | 104 | n/a |
| Llama 4 Scout | Small | 0 | 0 | 25 | 393 | n/a |
| MiniMax M3 | Frontier | 0 | 0 | 3 | 102 | n/a |
| Prompt | Tier | Hex | Google BigQuery | None | Other | A rate |
|---|---|---|---|---|---|---|
| ai-revenue-ops-copilot | Advanced | 40 | 10 | 15 | 443 | 80% |
| multi-tenant-crm | Advanced | 0 | 38 | 37 | 461 | 0% |
| ai-revenue-ops-copilot | Beginner | 20 | 0 | 5 | 495 | 100% |
| fitness-tracking-app | Advanced | 0 | 17 | 13 | 495 | 0% |
| ai-revenue-ops-copilot | Intermediate | 9 | 0 | 2 | 518 | 100% |
| url-shortener | Advanced | 0 | 8 | 5 | 520 | 0% |
| fitness-tracking-app | Intermediate | 0 | 0 | 17 | 520 | n/a |
| fitness-tracking-app | Beginner | 0 | 0 | 1 | 535 | n/a |
| multi-tenant-crm | Beginner | 0 | 0 | 47 | 486 | n/a |
| multi-tenant-crm | Intermediate | 0 | 0 | 33 | 498 | n/a |
| saas-application | Beginner | 0 | 0 | 18 | 519 | n/a |
| saas-application | Advanced | 0 | 0 | 31 | 505 | n/a |
| saas-application | Intermediate | 0 | 0 | 51 | 484 | n/a |
| url-shortener | Beginner | 0 | 0 | 110 | 425 | n/a |
| url-shortener | Intermediate | 0 | 0 | 75 | 461 | n/a |