ModelBench
Model catalog

Models

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

Compare Export CSV
7 models
Anthropic Has benchmarks
Ranked by Aider Polyglot
Anthropic: Claude Opus 4 (latest) T
72.0

Flagship Claude model for deep reasoning, coding, and long-horizon agents

anthropic/claude-opus-4-0 2025-05-22 200K context Input not listed Output not listed
2 providers
Anthropic: Claude Opus 4 T
Reasoning Tools 72.0

Flagship Claude model for deep reasoning, coding, and long-horizon agents

anthropic/claude-opus-4-20250514 2025-05-22 200K context $15/M input $75/M output
8 providers
Anthropic: Claude Sonnet 3.7 T
Reasoning Tools 64.9

Balanced Claude model for coding, analysis, agent workflows, and cost control

anthropic/claude-3-7-sonnet-20250219 2025-02-19 200K context $3/M input $15/M output
4 providers
Anthropic: Claude Sonnet 4 T
Reasoning Tools 61.3

Balanced Claude model for coding, analysis, agent workflows, and cost control

anthropic/claude-sonnet-4-20250514 2025-05-22 200K context $3/M input $15/M output
11 providers
Anthropic: Claude Sonnet 4 (latest) T
Reasoning Tools JSON 61.3

Balanced Claude model for coding, analysis, agent workflows, and cost control

anthropic/claude-sonnet-4-0 2025-05-22 200K context $2.898/M input $14.493/M output
4 providers
Anthropic: Claude Sonnet 3.5 v2 T
51.6

Balanced Claude model for coding, analysis, agent workflows, and cost control

anthropic/claude-3-5-sonnet-20241022 2024-10-22 200K context Input not listed Output not listed
1 provider
Anthropic: Claude Haiku 3.5 T
Tools 28.0

Fast Claude model for responsive assistance, classification, and lightweight agents

anthropic/claude-3-5-haiku-20241022 2024-10-22 200K context $0.8/M input $4/M output
3 providers