Public Benefits Bench v1.1
Professional Work · 2026-06-09
Social-services benchmark testing whether models can help people navigate SNAP benefits, eligibility, and application workflows.
Top models (higher is better)
| Model | Score |
|---|---|
| Claude Opus 5 | 76.9 |
| Claude Fable 5 | 70.4 |
| Kimi K3 | 68.3 |
| Opus 4.8 | 68.1 |
| GPT-5.6 Sol | 66.5 |
| Sonnet 5 | 66.0 |
| MiniMax M3 | 64.1 |
| DeepSeek-V4-Pro | 62.9 |
| Sonnet 4.6 | 62.4 |
| GPT-5.6 Terra | 62.4 |
| GLM-5.1 | 61.8 |
| Muse Spark 1.1 | 61.3 |
| GPT-5.6 Luna | 61.2 |
| GPT-5.5 | 60.9 |
| Gemini 3.5 Flash | 59.5 |
| Inkling-Small | 59.4 |
| Inkling | 58.5 |
| Kimi K2.6 | 56.6 |
| Gemini 3.6 Flash | 56.6 |
| Haiku 4.5 | 54.3 |
| Gemini 3.1 Pro Preview | 53.8 |
| Gemini 3.5 Flash-Lite | 51.8 |
| Grok 4.3 | 51.7 |
| Grok 4.1 Fast | 44.8 |
| Laguna M.1 | 43.8 |
| Laguna XS.2 | 41.4 |