| Metric | Value |
|---|---|
| Typesense wins | 112 |
| OpenSearch wins | 150 |
| Abstains (no tool) | 194 |
| Other tool chosen | 8805 |
| Decisive cases | 262 |
| Typesense win rate (unweighted) | 42.7% |
| 95% CI | 36.9% - 48.8% |
| Typesense win rate (weighted) | 42.7% |
Verified critics can leave comments here.
Verified critics can leave comments here.
| Model | Tier | Typesense | OpenSearch | None | Other | A rate |
|---|---|---|---|---|---|---|
| GPT 5.3 Codex | Frontier | 0 | 82 | 2 | 405 | 0% |
| Claude Sonnet 4.6 | Frontier | 51 | 0 | 0 | 438 | 100% |
| GPT 5.4 Mini | Mid | 1 | 30 | 4 | 448 | 3% |
| GPT 5.4 | Frontier | 1 | 23 | 1 | 446 | 4% |
| Claude Opus 4.6 | Frontier | 18 | 0 | 27 | 426 | 100% |
| Mistral Small 4 | Mid | 12 | 3 | 0 | 470 | 80% |
| MiniMax M2.7 | Frontier | 14 | 0 | 18 | 435 | 100% |
| DeepSeek V3.2 | Mid | 7 | 0 | 9 | 455 | 100% |
| Devstral 2 2512 | Mid | 1 | 5 | 1 | 480 | 17% |
| Llama 4 Maverick | Frontier | 4 | 0 | 1 | 484 | 100% |
| Claude Haiku 4.5 | Small | 2 | 2 | 3 | 461 | 50% |
| Gemini 2.5 Flash | Small | 0 | 3 | 49 | 419 | 0% |
| Claude Opus 4.8 | Frontier | 1 | 0 | 0 | 17 | 100% |
| Kimi K2.7 Code | Frontier | 0 | 1 | 0 | 16 | 0% |
| Qwen3 Coder Next | Mid | 0 | 1 | 7 | 479 | 0% |
| DeepSeek R1 0528 | Frontier | 0 | 0 | 8 | 481 | n/a |
| DeepSeek V4 Flash | Mid | 0 | 0 | 0 | 18 | n/a |
| DeepSeek V4 Pro | Frontier | 0 | 0 | 0 | 18 | n/a |
| Gemini 2.5 Pro | Frontier | 0 | 0 | 12 | 475 | n/a |
| Gemini 3.5 Flash | Small | 0 | 0 | 1 | 17 | n/a |
| GLM 5 Turbo | Frontier | 0 | 0 | 30 | 441 | n/a |
| GLM 5.2 | Frontier | 0 | 0 | 1 | 17 | n/a |
| GPT 5.5 | Frontier | 0 | 0 | 1 | 17 | n/a |
| Kimi K2.5 | Frontier | 0 | 0 | 5 | 462 | n/a |
| Llama 4 Scout | Small | 0 | 0 | 1 | 487 | n/a |
| MiMo V2 Pro | Frontier | 0 | 0 | 13 | 457 | n/a |
| MiMo V2.5 Pro | Frontier | 0 | 0 | 0 | 18 | n/a |
| MiniMax M3 | Frontier | 0 | 0 | 0 | 18 | n/a |
| Prompt | Tier | Typesense | OpenSearch | None | Other | A rate |
|---|---|---|---|---|---|---|
| social-media-platform | Advanced | 12 | 44 | 5 | 377 | 21% |
| ecommerce-store | Advanced | 24 | 20 | 2 | 392 | 55% |
| blog-platform-cms | Advanced | 26 | 16 | 3 | 391 | 62% |
| job-board | Advanced | 1 | 25 | 0 | 412 | 4% |
| ai-support-agent-platform | Beginner | 15 | 5 | 9 | 403 | 75% |
| blog-platform-cms | Advanced | 8 | 6 | 0 | 81 | 57% |
| social-media-platform | Advanced | 4 | 9 | 0 | 82 | 31% |
| ai-support-agent-platform | Advanced | 3 | 6 | 3 | 406 | 33% |
| ecommerce-store | Advanced | 0 | 9 | 0 | 86 | 0% |
| job-board | Advanced | 0 | 6 | 0 | 89 | 0% |
| job-board | Beginner | 4 | 0 | 1 | 431 | 100% |
| job-board | Intermediate | 3 | 0 | 0 | 435 | 100% |
| social-media-platform | Intermediate | 2 | 1 | 0 | 92 | 67% |
| ai-support-agent-platform | Intermediate | 2 | 0 | 5 | 424 | 100% |
| social-media-platform | Beginner | 2 | 0 | 6 | 430 | 100% |
| documentation-site | Advanced | 1 | 1 | 0 | 434 | 50% |
| job-board | Intermediate | 1 | 1 | 1 | 92 | 50% |
| social-media-platform | Intermediate | 1 | 1 | 0 | 436 | 50% |
| blog-platform-cms | Intermediate | 1 | 0 | 1 | 435 | 100% |
| ecommerce-store | Intermediate | 1 | 0 | 20 | 417 | 100% |
| job-board | Beginner | 1 | 0 | 0 | 94 | 100% |
| blog-platform-cms | Beginner | 0 | 0 | 12 | 83 | n/a |
| blog-platform-cms | Intermediate | 0 | 0 | 0 | 95 | n/a |
| blog-platform-cms | Beginner | 0 | 0 | 57 | 379 | n/a |
| documentation-site | Intermediate | 0 | 0 | 2 | 93 | n/a |
| documentation-site | Advanced | 0 | 0 | 0 | 95 | n/a |
| documentation-site | Beginner | 0 | 0 | 2 | 92 | n/a |
| documentation-site | Intermediate | 0 | 0 | 12 | 425 | n/a |
| documentation-site | Beginner | 0 | 0 | 10 | 426 | n/a |
| ecommerce-store | Intermediate | 0 | 0 | 0 | 95 | n/a |
| ecommerce-store | Beginner | 0 | 0 | 11 | 83 | n/a |
| ecommerce-store | Beginner | 0 | 0 | 29 | 408 | n/a |
| social-media-platform | Beginner | 0 | 0 | 3 | 92 | n/a |