| Metric | Value |
|---|---|
| Weaviate wins | 24 |
| Pinecone wins | 353 |
| Abstains (no tool) | 1 |
| Other tool chosen | 26 |
| Decisive cases | 377 |
| Weaviate win rate (unweighted) | 6.4% |
| 95% CI | 4.3% - 9.3% |
| Weaviate win rate (weighted) | 6.4% |
Verified critics can leave comments here.
Verified critics can leave comments here.
| Model | Tier | Weaviate | Pinecone | None | Other | A rate |
|---|---|---|---|---|---|---|
| Claude Sonnet 4.6 | Frontier | 7 | 14 | 0 | 0 | 33% |
| Llama 4 Maverick | Frontier | 2 | 19 | 0 | 0 | 10% |
| MiMo V2.5 Pro | Frontier | 2 | 19 | 0 | 0 | 10% |
| Claude Haiku 4.5 | Small | 0 | 21 | 0 | 0 | 0% |
| Gemini 2.5 Pro | Frontier | 0 | 21 | 0 | 0 | 0% |
| GPT 5.3 Codex | Frontier | 0 | 21 | 0 | 0 | 0% |
| GPT 5.5 | Frontier | 0 | 21 | 0 | 0 | 0% |
| Kimi K2.7 Code | Frontier | 0 | 21 | 0 | 0 | 0% |
| MiniMax M3 | Frontier | 0 | 21 | 0 | 0 | 0% |
| Qwen3 Coder Next | Mid | 0 | 21 | 0 | 0 | 0% |
| Llama 4 Scout | Small | 5 | 15 | 0 | 1 | 25% |
| DeepSeek R1 0528 | Frontier | 0 | 20 | 1 | 0 | 0% |
| Gemini 3.5 Flash | Small | 0 | 20 | 0 | 1 | 0% |
| GLM 5.2 | Frontier | 0 | 20 | 0 | 0 | 0% |
| DeepSeek V4 Pro | Frontier | 0 | 19 | 0 | 2 | 0% |
| GPT 5.4 Mini | Mid | 0 | 19 | 0 | 2 | 0% |
| DeepSeek V4 Flash | Mid | 3 | 15 | 0 | 3 | 17% |
| Devstral 2 2512 | Mid | 5 | 10 | 0 | 0 | 33% |
| Claude Opus 4.8 | Frontier | 0 | 13 | 0 | 8 | 0% |
| Mistral Small 4 | Mid | 0 | 3 | 0 | 9 | 0% |
| Prompt | Tier | Weaviate | Pinecone | None | Other | A rate |
|---|---|---|---|---|---|---|
| ai-agent-application | Beginner | 2 | 130 | 0 | 6 | 2% |
| ai-agent-application | Intermediate | 5 | 121 | 1 | 6 | 4% |
| ai-agent-application | Advanced | 17 | 102 | 0 | 14 | 14% |
