AnthropicReleased May 2025Proprietary
Claude Opus 4 is deprecated and can't be run here; try Claude Opus 5.5 (82.0% on Vision Evals) instead.
Claude Opus 4 has no score on the current Vision Evals. On the earlier Vision Evals board (last updated July 9, 2026) it passed 56.7% of visual understanding tasks (#57 of 77). It is a proprietary model from Anthropic, so commercial use follows Anthropic's terms.
This model is deprecated
Claude Opus 4 was deprecated on Jun 15, 2026 and can no longer be run here. Its evaluation results and details remain available for reference. Try Claude Opus 5.5 instead.
Claude Opus 4 has been deprecated by its provider and can no longer be evaluated on the current benchmark. The legacy Vision Evals results below are preserved for reference. See the current Vision Evals
| Category | Passed | Score |
|---|---|---|
| Document Understanding | 8 / 9 | 88.9% |
| Defect Detection | 10 / 15 | 66.7% |
| Object Understanding | 9 / 14 | 64.3% |
| Spatial Understanding | 11 / 19 | 57.9% |
| Object Counting | 0 / 10 | 0% |
Scores based on a single evaluation run · Methodology
View all legacy Vision Evals results →Claude 4 Opus, released by Anthropic in May 2025, is the flagship model of the Claude 4 family, built for complex, long-horizon reasoning and advanced coding workflows. It is multimodal, supporting text (including voice), images, and tool use, and operates as a hybrid reasoning model—able to deliver quick answers in fast mode or switch to extended thinking for deeper, multi-step problem solving. With a ~200,000-token context window and a training cutoff around March 2025, it is optimized for handling large documents, long conversations, and sophisticated agentic tasks.
Claude Opus 4 is proprietary: the weights are not distributed, and the Claude Opus 4 license is the vendor's commercial terms of service that you accept when you call the API.
Vendor terms govern data retention, whether your inputs can be trained on, rate limits, and regional availability, and they can change with notice. Review them if you handle regulated or customer data.
Proprietary terms are set by the vendor rather than negotiated per project, and no open-source obligation attaches to your code. If you would rather deploy an open model instead of Claude Opus 4, Roboflow's licensing page lists the models whose commercial license is included when you deploy on Roboflow.
Do not hesitate to reach out with questions for your commercial project. Our team will help you start solving business problems on the first call. See Roboflow commercial licensing for the models included in each plan.
Talk to salesLicense information is provided as a guide and is not legal advice.
Estimated cost per task vs. Visual Understanding score, for this model and others ranked near it. Upper-left is the sweet spot (high quality, low cost). Based on Vision Evals (legacy) results.
8 of 9 models plotted · 1 not yet evaluated
| Model | Score | Median tokens | Est. cost / task | Compare |
|---|---|---|---|---|
| Claude Sonnet 4.5 | 59.7% | 2.3K | $0.0092 | Compare |
| Claude Opus 4.1 | 59.7% | 2.1K | $0.040 | Compare |
| Claude Haiku 4.5 | 58.2% | 2.3K | $0.0030 | Compare |
| GPT-5 Nano | 58.2% | 2.7K | $0.0003 | Compare |
| Qwen3.5 397B A17B | 58.2% | 1.5K | $0.0009 | Compare |
| Claude Opus 4(this model) | 56.7% | — | — | — |
| Gemini 2.5 Flash | 55.2% | 476 | $0.0005 | Compare |
| Gemini 2.5 Flash-Lite | 53.7% | 301 | <$0.0001 | Compare |
| Kimi K2.5 | 35.8% | 2.7K | $0.0034 | Compare |
Other models worth comparing for similar use cases.
Other versions in the same family as Claude Opus 4.
Yes. Claude Opus 4 accepts image input, and on Roboflow's previous vision benchmark it passed 56.7% of visual understanding tasks (#57 of 77).
No. Claude Opus 4 has been deprecated by its provider and can no longer be run, so it is not part of Roboflow's current Vision Evals. Its results from the previous benchmark are preserved on this page for reference.