Claude 3.5 Sonnet
Language Available Full comparison ↗ anthropic/claude-3-5-sonnet · by Anthropic
· decoder-only-transformer
Pricing — 1 offering(s)
Input tokens
- $3.00 / 1M tokens (input) Current 2024-10-22 → present
Output tokens
- $15.00 / 1M tokens (output) Current 2024-10-22 → present
Showing the active price and any recorded history. Full pricing history is available via the paid API — see API docs.
See how Claude 3.5 Sonnet fits into a cost-aware routing setup
See how →Capability profile
reasoning strong
coding moderate
tool use strong
instruction following strong
context window strong
multilingual moderate
speed moderate
cost efficiency moderate
Coding benchmarks
View full leaderboard →| Benchmark | Score | Harness | Source |
|---|---|---|---|
| swe-bench-verified ↗ | 50.8% 2024-10 | agentless | 📊 leaderboard ↗ |
| aider-polyglot ↗ | 51.6% 2024-10 | aider | 📊 leaderboard ↗ |
| livecodebench ↗ | 38.9% 2025-01 | — | 📄 paper ↗ |
| bigcodebench ↗ | 30.4% 2025-04 | — | 📊 leaderboard ↗ |
Operator guidance
Previous generation; still widely deployed. Route here when Claude 3.5-era training is specifically required or for budget parity with Claude Sonnet 4. Step up to Claude Sonnet 4 for newer training data and improved instruction following.
Use cases
- Production coding and software engineering assistants
- Complex agentic tool-use pipelines
- Document analysis with large context
Limitations
- Training cutoff earlier than Claude Sonnet 4
- Capability ratings are qualitative, not a single cited benchmark run
Citations
Compare models
ComparingClaude 3.5 Sonnetwith
Pick a model above to see the comparison.