ModelBench
Model catalog

Models

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

Compare Export CSV
6 models
vivgrid
Ranked by OSWorld 2.0
Anthropic: Claude Opus 5.5 T
Reasoning Tools JSON 81.8

Claude model for long-running agentic coding and knowledge work

anthropic/claude-opus-5-5 2026-09-22 1M context $4/M input $20/M output
35 providers
OpenAI: GPT-6 Astra T
Reasoning Tools JSON 72.6

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 JSON 70.6

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
OpenAI: GPT-6 Sol T
Reasoning Tools JSON 60.5

OpenAI model for complex coding and agentic workflows

openai/gpt-6-sol 2026-09-22 1.05M context $2/M input $10/M output
33 providers
Google: Gemini 3.8 Flash T
Reasoning Tools JSON 59.0

Google's most intelligent Flash model, engineered for long-horizon software engineering, autonomous agents, and complex enterprise workflows

google/gemini-3.8-flash 2026-09-02 1.04858M context $0.75/M input $3.75/M output
32 providers
Anthropic: Claude Fable 5.1 T
Reasoning Tools JSON 41.7

Claude model for demanding reasoning and long-horizon agentic work

anthropic/claude-fable-5-1 2026-09-01 1M context $10/M input $50/M output
36 providers