← All benchmarks
Claude Opus 5 (Adaptive Reasoning, Max Effort)
Anthropic · Released 2026-07-24 · Independent benchmark scores from Artificial Analysis
Intelligence Index
50.7
Output speed
58.1
tokens/sec
Blended price
$10.00
per 1M tokens
Time to first token
33.71s
Model metadata
| Model ID | b8fc61f7-5e9a-49e6-8547-6ac56db24627 |
|---|---|
| Slug | claude-opus-5 |
| Release date | 2026-07-24 |
| Provider | Anthropic |
| Provider slug | anthropic |
| Output speed | 58.1 tok/s |
| Time to first token | 33.71s |
| Time to first answer | 33.71s |
| Blended price ($/1M) | $10.00 |
| Input price ($/1M) | $5.00 |
| Output price ($/1M) | $25.00 |
All evaluation scores (17)
| aime | — |
|---|---|
| aime 25 | — |
| artificial analysis coding index | 78.00 |
| artificial analysis intelligence index | 50.70 |
| artificial analysis math index | — |
| gpqa | 93.2% |
| hle | 54.9% |
| ifbench | — |
| lcr | 79.3% |
| livecodebench | — |
| math 500 | — |
| mmlu pro | — |
| scicode | 56.4% |
| tau banking | 42.1% |
| tau2 | — |
| terminalbench hard | — |
| terminalbench v2 1 | 89.1% |
Source: artificialanalysis.ai/models/claude-opus-5
Benchmark data from Artificial Analysis.