OpenGPT RESEARCH

AI model and agent evidence index

Use this index to move from an upstream source or provider to an exact model, Agent product, or benchmark record. Each destination states what its evidence covers and what it cannot prove.

Public ranking sources: 3
Model providers: 11
Model families: 13
Agent categories · Agent benchmarks: 7 · 9

Evidence scope

This page is an index of existing public evidence and provider-documented identities. Inclusion does not imply an OpenGPT endorsement or a universal rank.

How OpenGPT handles this evidence

The index is generated from the same reviewed model catalog, public leaderboard snapshots, first-party Agent identity directory, and benchmark records used by the visible rankings.

Comparison boundaries

Different sources measure different objects and must not be merged into one universal score.
Dates, versions, and configuration identity must be checked before acting on a result.
OpenGPT organizes public evidence; it does not claim to have rerun every listed evaluation.

Browse evidence hubs

Browse OpenGPT's public ranking sources, verified providers, model families, agent categories, and benchmark scopes from one crawlable research index.