| Metric | Value |
|---|---|
| Typesense wins | 117 |
| OpenSearch wins | 145 |
| Abstains (no tool) | 182 |
| Other tool chosen | 9167 |
| Decisive cases | 262 |
| Typesense win rate (unweighted) | 44.7% |
| 95% CI | 38.8% - 50.7% |
| Typesense win rate (weighted) | 44.7% |
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 | 76 | 1 | 426 | 0% |
| Claude Sonnet 4.6 | Frontier | 56 | 0 | 0 | 448 | 100% |
| GPT 5.4 Mini | Mid | 1 | 29 | 5 | 463 | 3% |
| GPT 5.4 | Frontier | 1 | 17 | 0 | 360 | 6% |
| Claude Opus 4.6 | Frontier | 17 | 0 | 21 | 340 | 100% |
| Mistral Small 4 | Mid | 10 | 2 | 0 | 487 | 83% |
| MiniMax M2.7 | Frontier | 11 | 0 | 12 | 351 | 100% |
| Llama 4 Maverick | Frontier | 6 | 0 | 2 | 496 | 100% |
| Claude Opus 4.8 | Frontier | 5 | 1 | 0 | 120 | 83% |
| Claude Haiku 4.5 | Small | 4 | 2 | 0 | 475 | 67% |
| GPT 5.5 | Frontier | 0 | 6 | 2 | 118 | 0% |
| Devstral 2 2512 | Mid | 0 | 5 | 1 | 459 | 0% |
| DeepSeek V3.2 | Mid | 3 | 0 | 7 | 368 | 100% |
| Gemini 2.5 Flash | Small | 0 | 3 | 41 | 334 | 0% |
| GLM 5.2 | Frontier | 1 | 1 | 2 | 122 | 50% |
| Kimi K2.7 Code | Frontier | 0 | 2 | 2 | 120 | 0% |
| DeepSeek V4 Flash | Mid | 1 | 0 | 3 | 121 | 100% |
| MiMo V2.5 Pro | Frontier | 1 | 0 | 2 | 122 | 100% |
| DeepSeek V4 Pro | Frontier | 0 | 1 | 6 | 119 | 0% |
| DeepSeek R1 0528 | Frontier | 0 | 0 | 10 | 494 | n/a |
| Gemini 2.5 Pro | Frontier | 0 | 0 | 14 | 489 | n/a |
| Gemini 3.5 Flash | Small | 0 | 0 | 5 | 121 | n/a |
| GLM 5 Turbo | Frontier | 0 | 0 | 27 | 351 | n/a |
| Kimi K2.5 | Frontier | 0 | 0 | 3 | 371 | n/a |
| Llama 4 Scout | Small | 0 | 0 | 1 | 501 | n/a |
| MiMo V2 Pro | Frontier | 0 | 0 | 12 | 365 | n/a |
| MiniMax M3 | Frontier | 0 | 0 | 0 | 126 | n/a |
| Qwen3 Coder Next | Mid | 0 | 0 | 3 | 500 | n/a |
| Prompt | Tier | Typesense | OpenSearch | None | Other | A rate |
|---|---|---|---|---|---|---|
| social-media-platform | Advanced | 14 | 57 | 5 | 460 | 20% |
| blog-platform-cms | Advanced | 32 | 20 | 4 | 479 | 62% |
| ecommerce-store | Advanced | 29 | 22 | 1 | 485 | 57% |
| job-board | Advanced | 2 | 31 | 1 | 503 | 6% |
| ai-support-agent-platform | Beginner | 17 | 5 | 11 | 496 | 77% |
| ai-support-agent-platform | Advanced | 3 | 7 | 3 | 500 | 30% |
| job-board | Beginner | 7 | 0 | 1 | 527 | 100% |
| ai-support-agent-platform | Intermediate | 4 | 1 | 6 | 518 | 80% |
| job-board | Intermediate | 3 | 0 | 0 | 534 | 100% |
| social-media-platform | Beginner | 2 | 0 | 5 | 530 | 100% |
| documentation-site | Advanced | 1 | 1 | 1 | 532 | 50% |
| social-media-platform | Intermediate | 1 | 1 | 1 | 533 | 50% |
| blog-platform-cms | Intermediate | 1 | 0 | 2 | 534 | 100% |
| ecommerce-store | Intermediate | 1 | 0 | 19 | 517 | 100% |
| blog-platform-cms | Beginner | 0 | 0 | 67 | 467 | n/a |
| documentation-site | Intermediate | 0 | 0 | 15 | 521 | n/a |
| documentation-site | Beginner | 0 | 0 | 10 | 525 | n/a |
| ecommerce-store | Beginner | 0 | 0 | 30 | 506 | n/a |