| Metric | Value |
|---|---|
| Tavily wins | 228 |
| SerpAPI wins | 42 |
| Abstains (no tool) | 1 |
| Other tool chosen | 27 |
| Decisive cases | 270 |
| Tavily win rate (unweighted) | 84.4% |
| 95% CI | 79.6% - 88.3% |
| Tavily win rate (weighted) | 84.4% |
Verified critics can leave comments here.
Verified critics can leave comments here.
| Model | Tier | Tavily | SerpAPI | None | Other | A rate |
|---|---|---|---|---|---|---|
| Claude Opus 4.8 | Frontier | 18 | 0 | 0 | 0 | 100% |
| Claude Sonnet 4.6 | Frontier | 18 | 0 | 0 | 0 | 100% |
| DeepSeek V4 Flash | Mid | 18 | 0 | 0 | 0 | 100% |
| GLM 5.2 | Frontier | 18 | 0 | 0 | 0 | 100% |
| GPT 5.3 Codex | Frontier | 18 | 0 | 0 | 0 | 100% |
| GPT 5.5 | Frontier | 18 | 0 | 0 | 0 | 100% |
| Kimi K2.7 Code | Frontier | 18 | 0 | 0 | 0 | 100% |
| Mistral Small 4 | Mid | 10 | 8 | 0 | 0 | 56% |
| GPT 5.4 Mini | Mid | 17 | 0 | 0 | 1 | 100% |
| MiniMax M3 | Frontier | 17 | 0 | 0 | 0 | 100% |
| DeepSeek V4 Pro | Frontier | 16 | 1 | 0 | 1 | 94% |
| DeepSeek R1 0528 | Frontier | 0 | 14 | 1 | 3 | 0% |
| Gemini 3.5 Flash | Small | 13 | 0 | 0 | 0 | 100% |
| MiMo V2.5 Pro | Frontier | 12 | 1 | 0 | 4 | 92% |
| Claude Haiku 4.5 | Small | 9 | 4 | 0 | 0 | 69% |
| Devstral 2 2512 | Mid | 0 | 13 | 0 | 0 | 0% |
| Qwen3 Coder Next | Mid | 7 | 0 | 0 | 0 | 100% |
| Llama 4 Maverick | Frontier | 1 | 1 | 0 | 8 | 50% |
| Llama 4 Scout | Small | 0 | 0 | 0 | 10 | n/a |
| Prompt | Tier | Tavily | SerpAPI | None | Other | A rate |
|---|---|---|---|---|---|---|
| ai-agent-application | Beginner | 81 | 11 | 0 | 9 | 88% |
| ai-agent-application | Advanced | 77 | 12 | 0 | 9 | 87% |
| ai-agent-application | Intermediate | 70 | 19 | 1 | 9 | 79% |
