Artificial Analysis for AI agents

Agents read Artificial Analysis at once. Changes and sends are held for a person's approval by default.

About Artificial Analysis

Artificial Analysis provides independent benchmarks and analysis of AI models and API providers — intelligence, coding and math indices, pricing, latency and throughput performance, plus arena rankings for image, video, speech and music models.

What an agent can do in Artificial Analysis

Every Artificial Analysis action is classed by the platform as a read, a change or a send. Reads run at once. Changes and sends are held for a person by default.

Runs at once (reads)

Looks things up in Artificial Analysis without asking first. 12 actions.

  • List Image-Editing Models (Arena)List image-editing models ranked by the Artificial Analysis arena, with Elo score and 95% confidence interval. Use to find the best-rated image-editing model. Returns all models in one call (unpaginat
  • List Image-to-Video-with-Audio Models (Arena)List image-to-video-with-audio models ranked by the Artificial Analysis arena, with Elo score and 95% confidence interval. Returns all models unpaginated in one call. No legacy sibling exists for this
  • List Image-to-Video Models (Arena)List image-to-video models ranked by the Artificial Analysis image-to-video arena, with Elo score and 95% confidence interval. Returns all models unpaginated in one call.
  • List Language Models (Intelligence & Pricing)List LLMs from the Artificial Analysis leaderboard with intelligence, coding and agentic indices, pricing, and performance (speed and latency). Pass the response's next_cursor back via `cursor` to fet
  • List Instrumental Music Models (Arena)List instrumental music-generation models ranked by the Artificial Analysis arena, with Elo score and 95% confidence interval. Returns all models in one call (unpaginated). Note: music items have no s
  • List Music-with-Vocals Models (Arena)List music-with-vocals generation models ranked by the Artificial Analysis arena, with Elo score and 95% confidence interval. Use to find the best-rated music-with-vocals model. Returns all models in
  • List Speech-to-Speech ModelsList speech-to-speech models with Big Bench Audio (bba_score), Full Duplex Bench (fdb_score), and Tau-Voice (tau_voice_score) quality scores. Tau-Voice uses each model's best result across providers.
  • List Speech-to-Text Models (WER)List speech-to-text (transcription) models with the Artificial Analysis overall word-error-rate index (aa_wer_index). Lower is better. Use to compare transcription accuracy across models. Returns all
  • List Text-to-Image Models (Arena)List text-to-image models ranked by the Artificial Analysis image arena, with Elo score and 95% confidence interval. Use to find the best-rated text-to-image model. Returns all models in one call (unp
  • List Text-to-Speech Models (Arena)List text-to-speech (TTS) models ranked by the Artificial Analysis arena, with Elo score and 95% confidence interval. Use to find the best-rated text-to-speech model. Returns all models in one call (u
  • List Text-to-Video-with-Audio Models (Arena)List text-to-video-with-audio models ranked by the Artificial Analysis arena, with Elo score and 95% confidence interval. No legacy sibling exists for this modality.
  • List Text-to-Video Models (Arena)List text-to-video models ranked by the Artificial Analysis arena, with Elo score and 95% confidence interval. Use to find the best-rated text-to-video model. Returns all models in one call (unpaginat

Held for approval by default (changes and sends)

Held for a person's approval by default. The approval is recorded and the action is sent once, never twice, with 10 seconds to undo. 0 actions.

None in this connector.

Artificial Analysis questions

Can an agent change data in Artificial Analysis on its own?

Not by default. Changes and sends in Artificial Analysis are held for a person's approval. The approval is recorded, and the action is sent once, never twice, with 10 seconds to undo.

What can an agent read in Artificial Analysis?

This connector lists 12 read actions. Reads run at once, without waiting for approval.

How does Artificial Analysis connect?

It connects with API key. Connectors are built and maintained by third-party developers; availability is confirmed during scoping.

Bring Artificial Analysis to your agents.