Leading: Intercom (66.5%)
| Metric | Value |
|---|---|
| Anthropic Claude API wins | 60 |
| Intercom wins | 119 |
| Abstains (no tool) | 93 |
| Other tool chosen | 3189 |
| Decisive cases | 179 |
| Anthropic Claude API win rate (unweighted) | 33.5% |
| 95% CI | 27.0% - 40.7% |
| Anthropic Claude API win rate (weighted) | 33.5% |
Verified critics can leave comments here.
Verified critics can leave comments here.
| Model | Tier | Anthropic Claude API | Intercom | None | Other | A rate |
|---|---|---|---|---|---|---|
| Claude Haiku 4.5 | Small | 44 | 7 | 0 | 134 | 86% |
| MiniMax M2.7 | Frontier | 16 | 8 | 0 | 96 | 67% |
| Llama 4 Scout | Small | 0 | 23 | 6 | 148 | 0% |
| Mistral Small 4 | Mid | 0 | 19 | 12 | 118 | 0% |
| Claude Sonnet 4.6 | Frontier | 0 | 16 | 0 | 170 | 0% |
| DeepSeek V3.2 | Mid | 0 | 13 | 0 | 118 | 0% |
| GPT 5.4 | Frontier | 0 | 9 | 0 | 123 | 0% |
| GPT 5.4 Mini | Mid | 0 | 8 | 1 | 175 | 0% |
| Llama 4 Maverick | Frontier | 0 | 5 | 18 | 157 | 0% |
| DeepSeek V4 Flash | Mid | 0 | 3 | 7 | 40 | 0% |
| Gemini 2.5 Pro | Frontier | 0 | 2 | 2 | 181 | 0% |
| MiMo V2 Pro | Frontier | 0 | 2 | 0 | 128 | 0% |
| MiMo V2.5 Pro | Frontier | 0 | 2 | 4 | 47 | 0% |
| DeepSeek R1 0528 | Frontier | 0 | 1 | 15 | 167 | 0% |
| Kimi K2.5 | Frontier | 0 | 1 | 1 | 116 | 0% |
| Claude Opus 4.6 | Frontier | 0 | 0 | 0 | 132 | n/a |
| Claude Opus 4.8 | Frontier | 0 | 0 | 0 | 53 | n/a |
| DeepSeek V4 Pro | Frontier | 0 | 0 | 9 | 45 | n/a |
| Devstral 2 2512 | Mid | 0 | 0 | 12 | 156 | n/a |
| Gemini 2.5 Flash | Small | 0 | 0 | 0 | 132 | n/a |
| Gemini 3.5 Flash | Small | 0 | 0 | 1 | 51 | n/a |
| GLM 5 Turbo | Frontier | 0 | 0 | 2 | 129 | n/a |
| GLM 5.2 | Frontier | 0 | 0 | 1 | 53 | n/a |
| GPT 5.3 Codex | Frontier | 0 | 0 | 0 | 185 | n/a |
| GPT 5.5 | Frontier | 0 | 0 | 0 | 49 | n/a |
| Kimi K2.7 Code | Frontier | 0 | 0 | 1 | 51 | n/a |
| MiniMax M3 | Frontier | 0 | 0 | 0 | 53 | n/a |
| Qwen3 Coder Next | Mid | 0 | 0 | 1 | 182 | n/a |
| Prompt | Tier | Anthropic Claude API | Intercom | None | Other | A rate |
|---|---|---|---|---|---|---|
| ai-support-agent-platform | Beginner | 1 | 118 | 1 | 390 | 1% |
| ai-support-agent-platform | Advanced | 33 | 0 | 1 | 495 | 100% |
| ai-revenue-ops-copilot | Advanced | 19 | 0 | 4 | 491 | 100% |
| ai-support-agent-platform | Intermediate | 4 | 1 | 0 | 526 | 80% |
| ai-revenue-ops-copilot | Intermediate | 2 | 0 | 1 | 526 | 100% |
| ai-revenue-ops-copilot | Beginner | 1 | 0 | 0 | 499 | 100% |
| 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 |