ModelBench
Model catalog

Models

Every model in the catalog with source-linked pricing, context limits, provider availability, and published benchmark results.

Compare Export CSV
5 models
File vivgrid
Ranked by BrowseComp
OpenAI: GPT-6 Astra T
Reasoning Tools JSON 91.5

GPT-6 Astra is OpenAI's most capable model for complex reasoning, coding, computer use, research, and document creation.

openai/gpt-6-astra 2026-09-04 1.05M context $10/M input $50/M output
35 providers
Anthropic: Claude Opus 5 T
Reasoning Tools 90.8

Strongest Claude Opus model for coding, agents, and professional work

anthropic/claude-opus-5 2026-07-24 1M context $5/M input $25/M output
41 providers
Anthropic: Claude Sonnet 5 T
Reasoning Tools 84.7

Everyday Claude agent model for coding, planning, browsing, and general work

anthropic/claude-sonnet-5 2026-06-30 1M context $2/M input $10/M output
43 providers
OpenAI: GPT-5.5 T
Reasoning Tools JSON 84.4

Default frontier GPT for coding, computer use, research, and knowledge work

openai/gpt-5.5 2026-04-23 1.05M context $5/M input $30/M output
50 providers
OpenAI: GPT-5.4 T
Reasoning Tools 82.7

Agent-ready GPT for coding and computer-use workflows at a lower cost

openai/gpt-5.4 2026-03-05 1.05M context $2.5/M input $15/M output
46 providers