Inference
EN
Vals AI

Public Benefits Bench v1

Can AI help people navigate SNAP benefits?

ModelsModels with a result.13
Top resultBest result on this benchmark.71.7%Claude Fable 5
Top-3 spreadPoints from first to third.11.0 pts
UpdatedDate the source changed the results.9 Jun 2026

Result and cost

13 of 13 results

Results

13 results
#ModelResultThe score from the source.CostUS dollars to run one task.TimeTime to run one task.
01Claude Fable 571.7% ±1.2$1.0517 min
02Claude Opus 4.862.1% ±1.3$1.3210 min
03MiniMax M360.7% ±1.3$0.19912 min
04Claude Sonnet 4.658.5% ±1.3$0.81613 min
05Gemini 3.5 Flash58.0% ±1.3$0.7765 min
06GLM-5.157.9% ±1.3$0.3397 min
07DeepSeek V4 Pro 042357.6% ±1.3$0.3616 min
08GPT-5.557.2% ±1.3$2.0226 min
09Kimi K2.653.4% ±1.3$0.61210 min
10Gemini 3.1 Pro Preview50.9% ±1.3$0.3013 min
11Grok 4.350.1% ±1.3$1.217 min
12Claude Haiku 4.549.5% ±1.3$0.1953 min
13Grok 4.1 Fast (Reasoning)44.3% ±1.3$0.0653 min