Leading: Anthropic (62.8%)
| Metric | Value |
|---|---|
| Anthropic Claude API wins | 51 |
| Anthropic wins | 86 |
| Abstains (no tool) | 6 |
| Other tool chosen | 2285 |
| Decisive cases | 137 |
| Anthropic Claude API win rate (unweighted) | 37.2% |
| 95% CI | 29.6% - 45.6% |
| Anthropic Claude API win rate (weighted) | 37.2% |
Verified critics can leave comments here.
Verified critics can leave comments here.
| Model | Tier | Anthropic Claude API | Anthropic | None | Other | A rate |
|---|---|---|---|---|---|---|
| Claude Haiku 4.5 | Small | 35 | 56 | 0 | 40 | 38% |
| MiniMax M2.7 | Frontier | 16 | 18 | 0 | 86 | 47% |
| Mistral Small 4 | Mid | 0 | 10 | 0 | 92 | 0% |
| GLM 5 Turbo | Frontier | 0 | 1 | 2 | 128 | 0% |
| Kimi K2.5 | Frontier | 0 | 1 | 1 | 116 | 0% |
| Claude Opus 4.6 | Frontier | 0 | 0 | 0 | 132 | n/a |
| Claude Sonnet 4.6 | Frontier | 0 | 0 | 0 | 132 | n/a |
| DeepSeek R1 0528 | Frontier | 0 | 0 | 0 | 129 | n/a |
| DeepSeek V3.2 | Mid | 0 | 0 | 0 | 131 | n/a |
| Devstral 2 2512 | Mid | 0 | 0 | 0 | 129 | n/a |
| Gemini 2.5 Flash | Small | 0 | 0 | 0 | 132 | n/a |
| Gemini 2.5 Pro | Frontier | 0 | 0 | 2 | 130 | n/a |
| GPT 5.3 Codex | Frontier | 0 | 0 | 0 | 132 | n/a |
| GPT 5.4 | Frontier | 0 | 0 | 0 | 132 | n/a |
| GPT 5.4 Mini | Mid | 0 | 0 | 1 | 131 | n/a |
| Llama 4 Maverick | Frontier | 0 | 0 | 0 | 127 | n/a |
| Llama 4 Scout | Small | 0 | 0 | 0 | 127 | n/a |
| MiMo V2 Pro | Frontier | 0 | 0 | 0 | 130 | n/a |
| Qwen3 Coder Next | Mid | 0 | 0 | 0 | 129 | n/a |
| Prompt | Tier | Anthropic Claude API | Anthropic | None | Other | A rate |
|---|---|---|---|---|---|---|
| ai-support-agent-platform | Advanced | 27 | 8 | 1 | 375 | 77% |
| ai-support-agent-platform | Intermediate | 4 | 23 | 0 | 387 | 15% |
| ai-revenue-ops-copilot | Intermediate | 2 | 24 | 1 | 385 | 8% |
| ai-revenue-ops-copilot | Advanced | 16 | 3 | 3 | 381 | 84% |
| ai-revenue-ops-copilot | Beginner | 1 | 18 | 0 | 369 | 5% |
| ai-support-agent-platform | Beginner | 1 | 10 | 1 | 388 | 9% |
