Benchmarks · knowledge
Public Benefits Bench v1.1
Accuracy answering questions about SNAP benefits and eligibility.
41 models · 41 results · updated 2026-10-12 · vals.ai ↗
Leaderboard
Opus 5 max
Heavy line: best score at each price. Thin lines join one model's effort levels. Cost uses each model's median subscription plan, or API price with no plan data. 29 more models under All models in settings.
More from this benchmark
1 published measuresTime per task50 results · lower is better
25 more models under All models in settings.
All results
41 rows| # | Model | Effort | Score | Subscription $ / task | API $ / task | Time |
|---|---|---|---|---|---|---|
| 1 | Opus 5 | max | 76.9% | $0.068 | $3.95 | 30 min |
| 2 | Fable 5.1 | max | 74.9% | $1.17 | $7.48 | 48 min |
| 3 | Opus 5.5 | max | 70.6% | $0.090 | $5.95 | 1.3 h |
| 4 | Fable 5 | max | 70.4% | $0.52 | $4.59 | 21 min |
| 5 | Gemini 4 Argon | high | 69.8% | $1.99 | $2.79 | 26 min |
| 6 | MiMo V2.6 Pro | max | 68.9% | $0.069 | $0.082 | 37 min |
| 7 | Hy4 preview | high | 68.6% | $0.19 | $0.25 | 1.0 h |
| 8 | GLM 5.3 | max | 68.5% | $0.098 | $0.95 | 36 min |
| 9 | Muse Spark 1.2 | xhigh | 68.5% | $0.29 | $0.59 | 8.9 min |
| 10 | Kimi K3 | max | 68.2% | $0.083 | $0.91 | 7.3 min |
| 11 | Opus 4.8 | max | 68.1% | $0.033 | $1.89 | 13 min |
| 12 | MiMo V2.6 Flash | high | 67.6% | free | $0.032 | 21 min |
| 13 | Sonnet 5.5 | max | 67.2% | $0.064 | $4.25 | 1.3 h |
| 14 | Qwen 3.8 Max | max | 67.1% | $0.12 | $0.99 | 41 min |
| 15 | Grok 4.6 | high | 66.8% | $0.094 | $0.92 | 26 min |
| 16 | GPT-5.6 Sol | max | 66.5% | $0.24 | $8.85 | 1.0 h |
| 17 | Sonnet 5 | max | 66.0% | $0.022 | $1.29 | 21 min |
| 18 | Grok 4.7 | xhigh | 65.6% | $0.21 | $2.25 | 17 min |
| 19 | Gemini 3.8 Flash | high | 65.3% | $0.041 | $1.01 | 3.4 min |
| 20 | DeepSeek V4.1 Flash | max | 64.3% | $0.005 | $0.073 | 10.0 min |
| 21 | MiniMax M3 | max | 64.1% | $0.043 | $0.25 | 12 min |
| 22 | Haiku 5.5 | max | 63.2% | $0.011 | $0.53 | 37 min |
| 23 | Sonnet 4.6 | max | 62.4% | $1.11 | $1.11 | 15 min |
| 24 | GPT-5.6 Terra | max | 62.4% | $0.033 | $1.20 | 20 min |
| 25 | GLM 5.1 | max | 61.8% | $0.089 | $0.34 | 9.7 min |
| 26 | Muse Spark 1.1 | xhigh | 61.3% | $0.28 | $0.28 | 6.6 min |
| 27 | GPT-5.6 Luna | max | 61.2% | $0.013 | $0.27 | 39 min |
| 28 | GPT-5.5 | xhigh | 60.9% | $0.11 | $3.97 | 40 min |
| 29 | Gemini 3.5 Flash | high | 59.5% | $1.11 | $1.11 | 5.6 min |
| 30 | Inkling Small | max | 59.4% | $0.077 | $0.096 | 8.7 min |