Leading: AI SDK (52.7%)
| Metric | Value |
|---|---|
| GCP Vertex AI wins | 35 |
| AI SDK wins | 39 |
| Abstains (no tool) | 93 |
| Other tool chosen | 3294 |
| Decisive cases | 74 |
| GCP Vertex AI win rate (unweighted) | 47.3% |
| 95% CI | 36.3% - 58.5% |
| GCP Vertex AI win rate (weighted) | 47.3% |
Verified critics can leave comments here.
Verified critics can leave comments here.
| Model | Tier | GCP Vertex AI | AI SDK | None | Other | A rate |
|---|---|---|---|---|---|---|
| Gemini 2.5 Flash | Small | 27 | 0 | 0 | 105 | 100% |
| Devstral 2 2512 | Mid | 8 | 19 | 12 | 129 | 30% |
| GLM 5 Turbo | Frontier | 0 | 14 | 2 | 115 | 0% |
| DeepSeek V3.2 | Mid | 0 | 2 | 0 | 129 | 0% |
| DeepSeek V4 Flash | Mid | 0 | 2 | 7 | 41 | 0% |
| GLM 5.2 | Frontier | 0 | 1 | 1 | 52 | 0% |
| MiniMax M2.7 | Frontier | 0 | 1 | 0 | 119 | 0% |
| Claude Haiku 4.5 | Small | 0 | 0 | 0 | 185 | n/a |
| Claude Opus 4.6 | Frontier | 0 | 0 | 0 | 132 | n/a |
| Claude Opus 4.8 | Frontier | 0 | 0 | 0 | 53 | n/a |
| Claude Sonnet 4.6 | Frontier | 0 | 0 | 0 | 186 | n/a |
| DeepSeek R1 0528 | Frontier | 0 | 0 | 15 | 168 | n/a |
| DeepSeek V4 Pro | Frontier | 0 | 0 | 9 | 45 | n/a |
| Gemini 2.5 Pro | Frontier | 0 | 0 | 2 | 183 | n/a |
| Gemini 3.5 Flash | Small | 0 | 0 | 1 | 51 | n/a |
| GPT 5.3 Codex | Frontier | 0 | 0 | 0 | 185 | n/a |
| GPT 5.4 | Frontier | 0 | 0 | 0 | 132 | n/a |
| GPT 5.4 Mini | Mid | 0 | 0 | 1 | 183 | n/a |
| GPT 5.5 | Frontier | 0 | 0 | 0 | 49 | n/a |
| Kimi K2.5 | Frontier | 0 | 0 | 1 | 117 | n/a |
| Kimi K2.7 Code | Frontier | 0 | 0 | 1 | 51 | n/a |
| Llama 4 Maverick | Frontier | 0 | 0 | 18 | 162 | n/a |
| Llama 4 Scout | Small | 0 | 0 | 6 | 171 | n/a |
| MiMo V2 Pro | Frontier | 0 | 0 | 0 | 130 | n/a |
| MiMo V2.5 Pro | Frontier | 0 | 0 | 4 | 49 | n/a |
| MiniMax M3 | Frontier | 0 | 0 | 0 | 53 | n/a |
| Mistral Small 4 | Mid | 0 | 0 | 12 | 137 | n/a |
| Qwen3 Coder Next | Mid | 0 | 0 | 1 | 182 | n/a |
| Prompt | Tier | GCP Vertex AI | AI SDK | None | Other | A rate |
|---|---|---|---|---|---|---|
| ai-revenue-ops-copilot | Advanced | 19 | 0 | 4 | 491 | 100% |
| ai-support-agent-platform | Beginner | 0 | 18 | 1 | 491 | 0% |
| ai-support-agent-platform | Intermediate | 0 | 16 | 0 | 515 | 0% |
| ai-support-agent-platform | Advanced | 8 | 3 | 1 | 517 | 73% |
| ai-revenue-ops-copilot | Beginner | 8 | 2 | 0 | 490 | 80% |
| ai-agent-application | Advanced | 0 | 0 | 18 | 98 | n/a |
| ai-agent-application | Beginner | 0 | 0 | 35 | 84 | n/a |
| ai-agent-application | Intermediate | 0 | 0 | 33 | 80 | n/a |
| ai-revenue-ops-copilot | Intermediate | 0 | 0 | 1 | 528 | n/a |