← All benchmarks
Claude Opus 5 (Adaptive Reasoning, Medium Effort)
Anthropic · Released 2026-07-24 · Independent benchmark scores from Artificial Analysis
Intelligence Index
45.1
Output speed
51.4
tokens/sec
Blended price
$10.00
per 1M tokens
Time to first token
8.71s
Model metadata
| Model ID | ff51be8f-e362-4a7e-9043-687ba15de207 |
|---|---|
| Slug | claude-opus-5-medium |
| Release date | 2026-07-24 |
| Provider | Anthropic |
| Provider slug | anthropic |
| Output speed | 51.4 tok/s |
| Time to first token | 8.71s |
| Time to first answer | 8.71s |
| Blended price ($/1M) | $10.00 |
| Input price ($/1M) | $5.00 |
| Output price ($/1M) | $25.00 |
All evaluation scores (17)
| aime | — |
|---|---|
| aime 25 | — |
| artificial analysis coding index | 74.30 |
| artificial analysis intelligence index | 45.10 |
| artificial analysis math index | — |
| gpqa | 91.9% |
| hle | 51.3% |
| ifbench | — |
| lcr | 82.0% |
| livecodebench | — |
| math 500 | — |
| mmlu pro | — |
| scicode | 51.5% |
| tau banking | 38.6% |
| tau2 | — |
| terminalbench hard | — |
| terminalbench v2 1 | 86.1% |
Source: artificialanalysis.ai/models/claude-opus-5-medium
Benchmark data from Artificial Analysis.