Leading: Vapi (60.0%)
| Metric | Value |
|---|---|
| Vectara wins | 2 |
| Vapi wins | 3 |
| Abstains (no tool) | 5 |
| Other tool chosen | 2198 |
| Decisive cases | 5 |
| Vectara win rate (unweighted) | 40.0% |
| 95% CI | 11.8% - 76.9% |
| Vectara win rate (weighted) | 40.0% |
Verified critics can leave comments here.
Verified critics can leave comments here.
| Model | Tier | Vectara | Vapi | None | Other | A rate |
|---|---|---|---|---|---|---|
| Devstral 2 2512 | Mid | 1 | 1 | 0 | 115 | 50% |
| DeepSeek R1 0528 | Frontier | 1 | 0 | 0 | 116 | 100% |
| DeepSeek V3.2 | Mid | 0 | 1 | 0 | 118 | 0% |
| Mistral Small 4 | Mid | 0 | 1 | 0 | 93 | 0% |
| Claude Haiku 4.5 | Small | 0 | 0 | 0 | 119 | n/a |
| Claude Opus 4.6 | Frontier | 0 | 0 | 0 | 120 | n/a |
| Claude Sonnet 4.6 | Frontier | 0 | 0 | 0 | 120 | n/a |
| Gemini 2.5 Flash | Small | 0 | 0 | 0 | 120 | n/a |
| Gemini 2.5 Pro | Frontier | 0 | 0 | 2 | 118 | n/a |
| GLM 5 Turbo | Frontier | 0 | 0 | 2 | 117 | n/a |
| GPT 5.3 Codex | Frontier | 0 | 0 | 0 | 120 | n/a |
| GPT 5.4 | Frontier | 0 | 0 | 0 | 120 | n/a |
| GPT 5.4 Mini | Mid | 0 | 0 | 0 | 120 | n/a |
| Kimi K2.5 | Frontier | 0 | 0 | 1 | 105 | n/a |
| Llama 4 Maverick | Frontier | 0 | 0 | 0 | 115 | n/a |
| Llama 4 Scout | Small | 0 | 0 | 0 | 116 | n/a |
| MiMo V2 Pro | Frontier | 0 | 0 | 0 | 118 | n/a |
| MiniMax M2.7 | Frontier | 0 | 0 | 0 | 109 | n/a |
| Qwen3 Coder Next | Mid | 0 | 0 | 0 | 119 | n/a |
| Prompt | Tier | Vectara | Vapi | None | Other | A rate |
|---|---|---|---|---|---|---|
| ai-support-agent-platform | Beginner | 2 | 2 | 1 | 359 | 50% |
| ai-revenue-ops-copilot | Beginner | 0 | 1 | 0 | 352 | 0% |
| ai-revenue-ops-copilot | Intermediate | 0 | 0 | 0 | 375 | n/a |
| ai-revenue-ops-copilot | Advanced | 0 | 0 | 3 | 362 | n/a |
| ai-support-agent-platform | Intermediate | 0 | 0 | 0 | 377 | n/a |
| ai-support-agent-platform | Advanced | 0 | 0 | 1 | 373 | n/a |