Claude 3.7 Sonnet (thinking)
ClaudeBalanced
This model is no longer available on Elosia. This page is kept for informational purposes.
Performance Tier
Balanced
Claude 3.7 Sonnet (thinking) is a balanced model from Claude : strong performance at a reasonable price.
Strong cost-performance ratio. Reliable for most professional use cases without premium pricing.
Capabilities
Context Length—
Max Output Tokens—
Benchmarks
General Intelligence
MMLU
85.8%
GPQA Diamond
62.4%
Mathematics
MATH-500
78.2%
Programming
HumanEval
87%
SWE-bench Verified
52.2%
Recommended Use Cases
CodingMathematicsAnalysisResearch
Strengths
- Extended thinking improves reasoning over base 3.7 Sonnet
- Good value for chain-of-thought tasks
- Visible reasoning process for transparency
Limitations
- Slower than base Sonnet due to thinking overhead
- Outperformed by Claude 4.x thinking models
Resources
This model may use your data for training