← All benchmarks
Claude 4 Opus (Reasoning)
Anthropic · Released 2025-05-22 · Independent benchmark scores from Artificial Analysis
Intelligence Index
20.6
Output speed
0.0
tokens/sec
Blended price
$30.00
per 1M tokens
Time to first token
0.00s
Model metadata
| Model ID | 8a4a5ead-7789-4389-8400-30e9d20370b7 |
|---|---|
| Slug | claude-4-opus-thinking |
| Release date | 2025-05-22 |
| Provider | Anthropic |
| Provider slug | anthropic |
| Output speed | 0.0 tok/s |
| Time to first token | 0.00s |
| Time to first answer | 0.00s |
| Blended price ($/1M) | $30.00 |
| Input price ($/1M) | $15.00 |
| Output price ($/1M) | $75.00 |
All evaluation scores (17)
| aime | 75.7% |
|---|---|
| aime 25 | 73.3% |
| artificial analysis coding index | — |
| artificial analysis intelligence index | 20.60 |
| artificial analysis math index | 73.30 |
| gpqa | 79.6% |
| hle | 12.3% |
| ifbench | 53.7% |
| lcr | 69.3% |
| livecodebench | 63.6% |
| math 500 | 98.2% |
| mmlu pro | 87.3% |
| scicode | — |
| tau banking | — |
| tau2 | 73.4% |
| terminalbench hard | 31.1% |
| terminalbench v2 1 | — |
Source: artificialanalysis.ai/models/claude-4-opus-thinking
Benchmark data from Artificial Analysis.