Anthropic
Claude 4 Opus (Non-reasoning)
Claude 4 Opus (Non-reasoning) is an Anthropic Claude Opus profile, representing the high-capability end of the Claude lineup for difficult coding, agentic, research, and computer-use tasks. This page compares the exact benchmarked variant against other Claude and non-Claude models on capability, runtime, and price.
Introducing Claude OpusOperational Metrics
Output Speed36.6 tok/s
First Token1.40s
Blended Price$30.00/M
Model Metadata
Queryable facts extracted from the upstream model payload.
ReleaseMay 22, 2025
Context Windown/a
Modalitiesn/a
Strength: MMLU-Pro
Rank #20 across 345 models.
86.0%
Strength: SciCode
Rank #79 across 472 models.
40.9%
Strength: Overall
Rank #119 across 500 models.
33.0
Watch Area: Value
Rank #318 across 323 models.
1.1
Watch Area: Output $
Rank #319 across 325 models.
$75.00/M
Watch Area: Blended $
Rank #318 across 325 models.
$30.00/M
Strength Profile
Percentile score by analysis domain.
* Cost is inverted: lower input, output, and blended prices rank higher.
Benchmark Percentiles
Higher bars mean stronger relative placement.
All Benchmarks
| Metric | Domain | Value | Rank |
|---|---|---|---|
| Artificial Analysis Intelligence Index | overall | 33.0 | #119 |
| Artificial Analysis Math Index | math | 36.3 | #171 |
| MMLU-Pro | reasoning | 86.0% | #20 |
| GPQA | reasoning | 70.1% | #197 |
| Humanity's Last Exam |