← All benchmarks
Claude Opus 5 (Adaptive Reasoning, Xhigh Effort)
Anthropic · Released 2026-07-24 · Independent benchmark scores from Artificial Analysis
Intelligence Index
49.7
Output speed
54.5
tokens/sec
Blended price
$10.00
per 1M tokens
Time to first token
24.56s
Model metadata
| Model ID | 1305c921-7aaa-4d6d-99b5-99b3acf15e19 |
|---|---|
| Slug | claude-opus-5-xhigh |
| Release date | 2026-07-24 |
| Provider | Anthropic |
| Provider slug | anthropic |
| Output speed | 54.5 tok/s |
| Time to first token | 24.56s |
| Time to first answer | 24.56s |
| Blended price ($/1M) | $10.00 |
| Input price ($/1M) | $5.00 |
| Output price ($/1M) | $25.00 |
All evaluation scores (17)
| aime | — |
|---|---|
| aime 25 | — |
| artificial analysis coding index | 77.00 |
| artificial analysis intelligence index | 49.70 |
| artificial analysis math index | — |
| gpqa | 93.7% |
| hle | 54.4% |
| ifbench | — |
| lcr | 80.3% |
| livecodebench | — |
| math 500 | — |
| mmlu pro | — |
| scicode | 55.7% |
| tau banking | 43.3% |
| tau2 | — |
| terminalbench hard | — |
| terminalbench v2 1 | 88.0% |
Source: artificialanalysis.ai/models/claude-opus-5-xhigh
Benchmark data from Artificial Analysis.