| Metric | Value |
|---|---|
| Humanloop wins | 55 |
| HumanFirst wins | 58 |
| Abstains (no tool) | 183 |
| Other tool chosen | 3526 |
| Decisive cases | 113 |
| Humanloop win rate (unweighted) | 48.7% |
| 95% CI | 39.7% - 57.8% |
| Humanloop win rate (weighted) | 48.7% |
Verified critics can leave comments here.
Verified critics can leave comments here.
| Model | Tier | Humanloop | HumanFirst | None | Other | A rate |
|---|---|---|---|---|---|---|
| Devstral 2 2512 | Mid | 24 | 58 | 14 | 81 | 29% |
| Gemini 2.5 Flash | Small | 14 | 0 | 1 | 112 | 100% |
| DeepSeek R1 0528 | Frontier | 6 | 0 | 9 | 189 | 100% |
| Claude Haiku 4.5 | Small | 4 | 0 | 3 | 187 | 100% |
| DeepSeek V3.2 | Mid | 4 | 0 | 22 | 102 | 100% |
| MiMo V2 Pro | Frontier | 2 | 0 | 8 | 122 | 100% |
| MiMo V2.5 Pro | Frontier | 1 | 0 | 8 | 62 | 100% |
| Claude Opus 4.6 | Frontier | 0 | 0 | 0 | 132 | n/a |
| Claude Opus 4.8 | Frontier | 0 | 0 | 6 | 65 | n/a |
| Claude Sonnet 4.6 | Frontier | 0 | 0 | 6 | 198 | n/a |
| DeepSeek V4 Flash | Mid | 0 | 0 | 4 | 67 | n/a |
| DeepSeek V4 Pro | Frontier | 0 | 0 | 2 | 70 | n/a |
| Gemini 2.5 Pro | Frontier | 0 | 0 | 11 | 191 | n/a |
| Gemini 3.5 Flash | Small | 0 | 0 | 7 | 65 | n/a |
| GLM 5 Turbo | Frontier | 0 | 0 | 19 | 113 | n/a |
| GLM 5.2 | Frontier | 0 | 0 | 0 | 72 | n/a |
| GPT 5.3 Codex | Frontier | 0 | 0 | 0 | 204 | n/a |
| GPT 5.4 | Frontier | 0 | 0 | 0 | 132 | n/a |
| GPT 5.4 Mini | Mid | 0 | 0 | 8 | 193 | n/a |
| GPT 5.5 | Frontier | 0 | 0 | 2 | 70 | n/a |
| Kimi K2.5 | Frontier | 0 | 0 | 3 | 116 | n/a |
| Kimi K2.7 Code | Frontier | 0 | 0 | 1 | 70 | n/a |
| Llama 4 Maverick | Frontier | 0 | 0 | 12 | 177 | n/a |
| Llama 4 Scout | Small | 0 | 0 | 20 | 165 | n/a |
| MiniMax M2.7 | Frontier | 0 | 0 | 5 | 124 | n/a |
| MiniMax M3 | Frontier | 0 | 0 | 5 | 67 | n/a |
| Mistral Small 4 | Mid | 0 | 0 | 3 | 186 | n/a |
| Qwen3 Coder Next | Mid | 0 | 0 | 4 | 194 | n/a |
| Prompt | Tier | Humanloop | HumanFirst | None | Other | A rate |
|---|---|---|---|---|---|---|
| ai-revenue-ops-copilot | Beginner | 12 | 20 | 11 | 483 | 38% |
| ai-revenue-ops-copilot | Intermediate | 17 | 1 | 4 | 500 | 94% |
| ai-support-agent-platform | Beginner | 3 | 13 | 73 | 438 | 19% |
| ai-revenue-ops-copilot | Advanced | 8 | 7 | 3 | 496 | 53% |
| ai-support-agent-platform | Intermediate | 10 | 4 | 6 | 502 | 71% |
| ai-support-agent-platform | Advanced | 4 | 6 | 5 | 512 | 40% |
| ai-engineering-workflow | Intermediate | 0 | 5 | 1 | 106 | 0% |
| ai-engineering-workflow | Advanced | 0 | 2 | 1 | 109 | 0% |
| ai-agent-application | Intermediate | 1 | 0 | 1 | 111 | 100% |
| ai-agent-application | Advanced | 0 | 0 | 0 | 112 | n/a |
| ai-agent-application | Beginner | 0 | 0 | 25 | 94 | n/a |
| ai-engineering-workflow | Beginner | 0 | 0 | 53 | 63 | n/a |