← All benchmarks
Claude 4 Sonnet (Reasoning)
Anthropic · Released 2025-05-22 · Independent benchmark scores from Artificial Analysis
Intelligence Index
18.9
Output speed
0.0
tokens/sec
Blended price
$6.00
per 1M tokens
Time to first token
0.00s
Model metadata
| Model ID | a7564055-f8ba-4c4b-9e2d-060f61263645 |
|---|---|
| Slug | claude-4-sonnet-thinking |
| Release date | 2025-05-22 |
| Provider | Anthropic |
| Provider slug | anthropic |
| Output speed | 0.0 tok/s |
| Time to first token | 0.00s |
| Time to first answer | 0.00s |
| Blended price ($/1M) | $6.00 |
| Input price ($/1M) | $3.00 |
| Output price ($/1M) | $15.00 |
All evaluation scores (17)
| aime | 77.3% |
|---|---|
| aime 25 | 74.3% |
| artificial analysis coding index | 37.60 |
| artificial analysis intelligence index | 18.90 |
| artificial analysis math index | 74.30 |
| gpqa | 77.7% |
| hle | 10.7% |
| ifbench | 54.7% |
| lcr | 70.3% |
| livecodebench | 65.5% |
| math 500 | 99.1% |
| mmlu pro | 84.2% |
| scicode | — |
| tau banking | 16.7% |
| tau2 | 64.6% |
| terminalbench hard | 31.1% |
| terminalbench v2 1 | 36.3% |
Source: artificialanalysis.ai/models/claude-4-sonnet-thinking
Benchmark data from Artificial Analysis.