← All benchmarks
Claude Opus 5 (Adaptive Reasoning, High Effort)
Anthropic · Released 2026-07-24 · Independent benchmark scores from Artificial Analysis
Intelligence Index
48.2
Output speed
53.7
tokens/sec
Blended price
$10.00
per 1M tokens
Time to first token
17.07s
Model metadata
| Model ID | 712be54a-77ae-41b2-9a58-21181479d6ee |
|---|---|
| Slug | claude-opus-5-high |
| Release date | 2026-07-24 |
| Provider | Anthropic |
| Provider slug | anthropic |
| Output speed | 53.7 tok/s |
| Time to first token | 17.07s |
| Time to first answer | 17.07s |
| Blended price ($/1M) | $10.00 |
| Input price ($/1M) | $5.00 |
| Output price ($/1M) | $25.00 |
All evaluation scores (17)
| aime | — |
|---|---|
| aime 25 | — |
| artificial analysis coding index | 76.50 |
| artificial analysis intelligence index | 48.20 |
| artificial analysis math index | — |
| gpqa | 93.7% |
| hle | 52.8% |
| ifbench | — |
| lcr | 79.0% |
| livecodebench | — |
| math 500 | — |
| mmlu pro | — |
| scicode | 55.4% |
| tau banking | 44.7% |
| tau2 | — |
| terminalbench hard | — |
| terminalbench v2 1 | 87.6% |
Source: artificialanalysis.ai/models/claude-opus-5-high
Benchmark data from Artificial Analysis.