🇺🇸 United States🧠 GeneralistReleased October 2025
Claude Sonnet 4.6
Anthropic
FreeRGPD
Verdict
A good performance/compliance balance for a European company.
Overview
Claude Sonnet 4.6 is the most-used model in the lineup: it delivers 90% of Opus capabilities at 5x lower price and higher speed. It's the default pick for most use cases: assistance, coding, content, support. French quality is excellent.
Skill profile
Arena Elo1352
Verified benchmarks
GPQA65.4%
SWE-Bench65%
MATH82.1%
MMLU86.2%
HumanEval91.5%
What do these scores mean?
GPQA65.4%very good
PhD-level science questions (physics, chemistry, biology), with no tool access.
SWE-Bench65%very good
Resolving real GitHub issues under real conditions (SWE-bench Verified).
MATH82.1%excellent
Competition-level math problems.
MMLU86.2%excellent
General knowledge across dozens of academic subjects.
HumanEval91.5%world-class
Python code generation from specifications.
Strengths
- Excellent at code
- Strong French quality
- World-class on Arena
- Has a free tier
Who is it for
A good fit if…
- you build with a coding agent
- you work in French
- you have GDPR constraints
Skip it if…
Ideal use cases
- Daily assistant
- Pair-programming
- Summarization
- Content creation
- Support chatbots
Access & availability
Paid API per tokenFree tier availableConsumer subscription (~20€/mo)
Key specifications
Context
200K
Input price
$3.00 $/M
Output price
$15.00 $/M
Speed
110 tok/s
Price not auditedBenchmarks not audited
Estimate your monthly cost
Per-token API pricing$196/ month with Claude Sonnet 4.6
For the same usage
- DeepSeek V3$16-92%
- GPT-5$108-45%
- Grok 4$256+31%
Indicative estimate based on standard API rates (excluding caching, batch and volume discounts). Always check the official pricing before committing.
Privacy
GDPR-compliantHosting : US/EUAnonymizable data
Advanced data · for expertsArchitecture, modalities, detailed cost, full benchmarks▾
Advanced data · for experts
Architecture, modalities, detailed cost, full benchmarks
Architecture
Dense
Size
undisclosed
Cutoff date
Mar 2025
Inputs
text, image, document
Outputs
text, code
License
commercial
Hosting
US/EU
Hallucination score
5/5
Estimated cost (API)
Typical exchange (~3k in / 1k out)
≈ $0.0240
1M in + 1M out
≈ $18.00
All benchmarks
| Arena Elo | 1352 |
| MMLU | 86.2% |
| GPQA | 65.4% |
| HumanEval | 91.5% |
| SWE-Bench | 65.0% |
| MATH | 82.1% |