Skip to main content

LlmBench AI Provider Support and WebViews

Understand LlmBench account-backed WebViews, native provider transports, gateway adapters, and the current compatibility boundary.
3 min read

LlmBench combines account-backed provider WebViews with a native chat/compare layer. Provider-specific behavior stays behind bounded adapters instead of leaking across the UI.

Account-backed WebViews#

The current Android client includes WebView entries for ChatGPT, Claude, Gemini, DeepSeek, Kimi, Mistral Vibe, Qwen, Microsoft Copilot, Z.ai, Grok, Character.AI, Venice, and Meta AI.

Warning

"Integrated" does not guarantee that every provider permits fresh embedded sign-in. Authentication remains between the provider page and that provider, and LlmBench does not scrape passwords, cookies, OAuth tokens, or page contents.

ProviderStatusUploadsActivity trackingNotes
ChatGPTFullYesGenerating + unreadPersistent provider-scoped session
ClaudeFullYesGenerating + unreadPersistent provider-scoped session
Gemini ChatPartialYesGenerating + unreadFresh Google OAuth may be blocked in embedded user-agents
DeepSeekFullYesGenerating + unreadPersistent session
KimiFullYesGenerating + unreadPersistent session
Mistral VibeFullYesGenerating + unreadProvider-scoped activity probe
QwenPartialProvider-documented; embedded flow unverifiedNot yetEmbedded sign-in/upload verification pending
Microsoft CopilotPartialProvider-documented; embedded flow unverifiedNot yetProvider-owned auth hosts are bounded in-WebView
Z.aiPartialPage-driven; embedded flow unverifiedNot yetProvider-owned auth hosts are bounded in-WebView
GrokPartialProvider-documented; embedded flow unverifiedNot yetActivity probe still needs verification
Character.AIPartialProvider-documented image attachments; embedded flow unverifiedNot yetSign-in/upload verification pending
VenicePartialProvider-documented; embedded flow unverifiedNot yetSign-in/upload verification pending
Meta AIPartialNot verifiedNot yetProvider-owned Meta login surface

Native and free-provider layer#

The native chat layer is already implemented, not merely planned:

  • Gemini through generateContent REST with streaming support.
  • OpenAI through the Responses API with store=false and bounded visible-text replay.
  • Claude through its native API transport.
  • OpenRouter Free through the shared OpenAI-compatible gateway adapter.
  • AIHubMix Free through the same gateway boundary.

The two gateway aggregators stay outside the default All Models comparison so the same underlying model is not routed twice.

Provider tweaks and diagnostics#

Provider tweaks live in a small, auditable in-app registry. Scripts are static, scoped to matching provider hosts, and applied after page load; remote userscript code is never fetched. Diagnostics expose only privacy-safe integration metadata such as provider host, WebView package/version, capability counts, activity-tracking support, and file-picker events. They do not collect page text, full URLs, form values, file names, cookies, or authentication tokens.

Note

Compatibility for newer providers is intentionally marked partial until embedded sign-in, uploads, and provider-specific generation tracking are verified in the Android WebView.

Gemini and embedded Google sign-in#

Gemini Chat is integrated, but Google may reject OAuth flows from embedded user-agents. That is a provider policy boundary, not something LlmBench attempts to bypass.