Claude 4 Sonnet
AnthropicProprietaryNon-reasoningProvisionalReleased May 22, 2025
Overall score
38.1
Rank 149 of 222 · 28.4–47.8
Context window
200K
200,000 tokens
Price per 1M tokens
$3.00 in · $15.00 out
Source: BenchLM
Blended price
$6.00
3:1 input:output tokens
Output speed
—
Not measured yet
Category scores
Scores per capability area with the model's rank among ranked models in that category.
- 1Coding59.4
- 2Multimodal56.4
- 3Reasoning55.2
- 4Instruction following#8653.5
- 5Knowledge45.2
Benchmark results (4)
As reported in system cards, papers and public evaluations. Position compares this model with every other model reporting the same benchmark.
Agentic & tool use
| Gert Labs | 39.66 | #38 of 52 |
| JobBench | 18.4 | #29 of 34 |
Coding
| SWE-bench Verified | 72.7 | #51 of 98 |
Math
| AIME 2025 | 33.1 | #34 of 38 |
Pricing by source
USD per 1M tokens.
| Source | Input | Output | Cached in |
|---|---|---|---|
| List price (BenchLM) | $3.00 | $15.00 | — |
Anthropic's pricing docs list Claude Sonnet 4 at $3 input / $15 output per million tokens.
Speed
Measured by us through OpenRouter (median of trials).
Not available on OpenRouter, so we cannot measure it yet.
Related models
Similar score
- o138.3 · $26.25
- LFM2.5-24B-A2B37.7 · $0.33
- GPT-4.137.6 · $3.50
- GPT-5 nano37.3 · $0.14
- GPT-OSS 120B37.3 · $0.26