Model comparison
Claude Opus 5 and Kimi K3.1 Pro compared on price, context window, capabilities and published benchmarks. Data comes from the OpenModels registry.
| Specification | Claude Opus 5 | Kimi K3.1 Pro |
|---|---|---|
| Developer | Anthropic | Kimi |
| Released | Jul 21, 2026 | Oct 23, 2026 |
| Context window | 300K tokens | 1.05M tokens |
| Input price / 1M | $5.00via Anthropic | $2.00via Moonshot AI |
| Output price / 1M | $25.00via Anthropic | $10.00via Moonshot AI |
| Providers | 1 | 1 |
| License | proprietary | other |
| Input modalities | code, image, text | code, image, text, video |
| Capabilities | chat, completion, function-calling, vision, code-generation, reasoning | chat, completion, function-calling, vision, code-generation, reasoning |
| Reasoning | Yes | Yes |
| Tool calling | Yes | Yes |
Only benchmarks with a published score for at least one of the two models are shown. Published scores with their sources. Vendor-reported results use the vendor's own evaluation settings and are not directly comparable across vendors.
| — |
| GDPval-AA 2.1 | 1,708Anthropic · Vendor-reported | — |
|---|
| Humanity's Last Exam | 63.6%Anthropic · Vendor-reported | — |
|---|
| OSWorld 2.1 | 74%Anthropic · Vendor-reported | — |
|---|
| Terminal-Bench 4.0 | 52.3%Anthropic · Vendor-reported | — |
|---|
| Terminal-Bench-Science 0.1 | 29%Anthropic · Vendor-reported | — |
|---|