| Metric | Value |
|---|---|
| Hex wins | 72 |
| Google BigQuery wins | 74 |
| Abstains (no tool) | 459 |
| Other tool chosen | 7360 |
| Decisive cases | 146 |
| Hex win rate (unweighted) | 49.3% |
| 95% CI | 41.3% - 57.3% |
| Hex win rate (weighted) | 49.3% |
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 | 37 | 0 | 3 | 363 | 100% |
| Llama 4 Maverick | Frontier | 1 | 23 | 0 | 395 | 4% |
| GPT 5.3 Codex | Frontier | 0 | 19 | 1 | 399 | 0% |
| Devstral 2 2512 | Mid | 9 | 0 | 0 | 394 | 100% |
| Kimi K2.5 | Frontier | 8 | 0 | 23 | 280 | 100% |
| GPT 5.4 | Frontier | 6 | 2 | 0 | 319 | 75% |
| DeepSeek R1 0528 | Frontier | 0 | 8 | 149 | 261 | 0% |
| Qwen3 Coder Next | Mid | 0 | 7 | 5 | 408 | 0% |
| Claude Opus 4.6 | Frontier | 4 | 0 | 1 | 325 | 100% |
| MiniMax M2.7 | Frontier | 4 | 0 | 36 | 279 | 100% |
| GPT 5.4 Mini | Mid | 0 | 4 | 7 | 408 | 0% |
| GPT 5.5 | Frontier | 0 | 4 | 1 | 82 | 0% |
| MiMo V2 Pro | Frontier | 0 | 3 | 25 | 302 | 0% |
| Gemini 2.5 Pro | Frontier | 0 | 2 | 26 | 388 | 0% |
| MiMo V2.5 Pro | Frontier | 0 | 2 | 11 | 77 | 0% |
| Claude Opus 4.8 | Frontier | 1 | 0 | 0 | 88 | 100% |
| DeepSeek V4 Pro | Frontier | 1 | 0 | 15 | 73 | 100% |
| Kimi K2.7 Code | Frontier | 1 | 0 | 3 | 86 | 100% |
| Claude Haiku 4.5 | Small | 0 | 0 | 5 | 401 | n/a |
| Claude Sonnet 4.6 | Frontier | 0 | 0 | 1 | 419 | n/a |
| DeepSeek V3.2 | Mid | 0 | 0 | 27 | 300 | n/a |
| DeepSeek V4 Flash | Mid | 0 | 0 | 4 | 84 | n/a |
| Gemini 2.5 Flash | Small | 0 | 0 | 22 | 305 | 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 |
| Llama 4 Scout | Small | 0 | 0 | 25 | 393 | n/a |
| MiniMax M3 | Frontier | 0 | 0 | 3 | 87 | n/a |
| Prompt | Tier | Hex | Google BigQuery | None | Other | A rate |
|---|---|---|---|---|---|---|
| ai-revenue-ops-copilot | Advanced | 41 | 10 | 16 | 439 | 80% |
| multi-tenant-crm | Advanced | 0 | 39 | 37 | 460 | 0% |
| ai-revenue-ops-copilot | Beginner | 21 | 0 | 5 | 494 | 100% |
| fitness-tracking-app | Advanced | 0 | 17 | 13 | 496 | 0% |
| ai-revenue-ops-copilot | Intermediate | 10 | 0 | 3 | 516 | 100% |
| url-shortener | Advanced | 0 | 8 | 5 | 519 | 0% |
| fitness-tracking-app | Intermediate | 0 | 0 | 16 | 521 | n/a |
| fitness-tracking-app | Beginner | 0 | 0 | 1 | 535 | n/a |
| multi-tenant-crm | Beginner | 0 | 0 | 47 | 487 | n/a |
| multi-tenant-crm | Intermediate | 0 | 0 | 34 | 496 | n/a |
| saas-application | Beginner | 0 | 0 | 16 | 521 | n/a |
| saas-application | Intermediate | 0 | 0 | 52 | 483 | n/a |
| saas-application | Advanced | 0 | 0 | 30 | 506 | n/a |
| url-shortener | Beginner | 0 | 0 | 109 | 427 | n/a |
| url-shortener | Intermediate | 0 | 0 | 75 | 460 | n/a |