Claude Sonnet 4
ActiveBalanced mid-tier Claude model with strong general capability and price.
Overview
Claude Sonnet 4 balances intelligence and cost. Widely used for production coding, agents, and content workflows.
Benchmarks
| Benchmark | Score | Source |
|---|---|---|
| HumanEvalCoding | 92pass@1 % | Self-reported Anthropic model card |
| MMLUGeneral knowledge | 83.1% accuracy | Self-reported Anthropic model card |
| SWE-bench VerifiedCoding | 44% resolved | Self-reported Anthropic model card |
Integrations & tooling support
- Tool calling
- Supported
- Structured outputs
- Supported
Price vs quality
Poor value
Below-average benchmark performance for the price.
- Quality percentile
- 37.5%
- Effective price
- $12/1M
- Pricing breakdown
- $3/1M in
$15/1M out
vs 3 benchmarks
/ 1M tokens (input + 3× output)
Community ratings
No ratings yet. Be the first to rate Claude Sonnet 4.
Rate Claude Sonnet 4
Sign in to rate and review.
Comments
Sign in to leave a comment.