| Metric | Value |
|---|---|
| Braintrust wins | 1243 |
| LangSmith wins | 1200 |
| Abstains (no tool) | 183 |
| Other tool chosen | 1196 |
| Decisive cases | 2443 |
| Braintrust win rate (unweighted) | 50.9% |
| 95% CI | 48.9% - 52.9% |
| Braintrust win rate (weighted) | 50.9% |
Verified critics can leave comments here.
Verified critics can leave comments here.
| Model | Tier | Braintrust | LangSmith | None | Other | A rate |
|---|---|---|---|---|---|---|
| GPT 5.3 Codex | Frontier | 193 | 10 | 0 | 1 | 95% |
| Claude Haiku 4.5 | Small | 162 | 18 | 3 | 11 | 90% |
| Claude Sonnet 4.6 | Frontier | 94 | 76 | 6 | 28 | 55% |
| DeepSeek R1 0528 | Frontier | 0 | 169 | 9 | 26 | 0% |
| Gemini 2.5 Pro | Frontier | 1 | 152 | 11 | 38 | 1% |
| GPT 5.4 Mini | Mid | 5 | 131 | 8 | 57 | 4% |
| Qwen3 Coder Next | Mid | 0 | 135 | 4 | 59 | 0% |
| Mistral Small 4 | Mid | 0 | 129 | 3 | 57 | 0% |
| Claude Opus 4.6 | Frontier | 113 | 1 | 0 | 18 | 99% |
| GPT 5.4 | Frontier | 92 | 18 | 0 | 22 | 84% |
| Kimi K2.5 | Frontier | 109 | 0 | 3 | 7 | 100% |
| GLM 5 Turbo | Frontier | 84 | 18 | 19 | 11 | 82% |
| MiniMax M2.7 | Frontier | 31 | 62 | 5 | 31 | 33% |
| DeepSeek V3.2 | Mid | 0 | 80 | 22 | 26 | 0% |
| GPT 5.5 | Frontier | 66 | 1 | 2 | 3 | 99% |
| MiMo V2 Pro | Frontier | 1 | 62 | 8 | 61 | 2% |
| MiniMax M3 | Frontier | 58 | 2 | 5 | 7 | 97% |
| DeepSeek V4 Pro | Frontier | 38 | 17 | 2 | 15 | 69% |
| Gemini 3.5 Flash | Small | 53 | 0 | 7 | 12 | 100% |
| Kimi K2.7 Code | Frontier | 53 | 0 | 1 | 17 | 100% |
| GLM 5.2 | Frontier | 44 | 1 | 0 | 27 | 98% |
| Claude Opus 4.8 | Frontier | 18 | 27 | 6 | 20 | 40% |
| MiMo V2.5 Pro | Frontier | 25 | 16 | 8 | 22 | 61% |
| Llama 4 Maverick | Frontier | 0 | 38 | 12 | 139 | 0% |
| DeepSeek V4 Flash | Mid | 3 | 25 | 4 | 39 | 11% |
| Devstral 2 2512 | Mid | 0 | 9 | 14 | 154 | 0% |
| Gemini 2.5 Flash | Small | 0 | 3 | 1 | 123 | 0% |
| Llama 4 Scout | Small | 0 | 0 | 20 | 165 | n/a |
| Prompt | Tier | Braintrust | LangSmith | None | Other | A rate |
|---|---|---|---|---|---|---|
| ai-revenue-ops-copilot | Intermediate | 167 | 225 | 4 | 126 | 43% |
| ai-support-agent-platform | Intermediate | 123 | 253 | 6 | 140 | 33% |
| ai-revenue-ops-copilot | Advanced | 216 | 152 | 3 | 143 | 59% |
| ai-revenue-ops-copilot | Beginner | 199 | 152 | 11 | 164 | 57% |
| ai-support-agent-platform | Advanced | 175 | 173 | 5 | 174 | 50% |
| ai-support-agent-platform | Beginner | 137 | 114 | 73 | 203 | 55% |
| ai-agent-application | Advanced | 45 | 25 | 0 | 42 | 64% |
| ai-engineering-workflow | Intermediate | 51 | 16 | 1 | 44 | 76% |
| ai-agent-application | Intermediate | 38 | 29 | 1 | 45 | 57% |
| ai-engineering-workflow | Advanced | 50 | 14 | 1 | 47 | 78% |
| ai-agent-application | Beginner | 22 | 33 | 25 | 39 | 40% |
| ai-engineering-workflow | Beginner | 20 | 14 | 53 | 29 | 59% |
