Vals AI Web Search: leaderboard
Vals AI web-search comparison over expert-authored legal and financial research tasks, pitting native provider search against independent tools; accuracy (%) is all-pass on legal and dealbreaker-gated partial credit on finance.
Metric: Accuracy (%). Source: www.vals.ai. Saturation forecast: Around August 2028. 9 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | GPT-5.6 Sol (Max) | 49.08 | #22 (GPT-5.6 Sol) |
| 2 | Claude Fable 5 (Max) | 48.45 | #20 (Claude Fable 5) |
| 3 | Grok 4.5 (High) | 38.75 | #55 (Grok 4.5) |
| 4 | Gemini 3.5 Flash (High) | 37.04 | #67 (Gemini 3.5 Flash) |
No result here: #3 Claude Opus 5.5, #5 GPT-6 Astra, #6 GPT-6.1 Sol.
Interactive version: theaggregate.ai/benchmark?slug=vals-ai-web-search · How It Works · Data refreshed daily, snapshot 2026-11-06.