Model comparison
Claude Opus 5.5 and GPT-OSS 120B compared on price, context window, capabilities and published benchmarks. Data comes from the OpenModels registry.
| Specification | Claude Opus 5.5 | GPT-OSS 120B |
|---|---|---|
| Developer | Anthropic | Openai |
| Released | Sep 22, 2026 | Apr 1, 2026 |
| Context window | 1M tokens | 131K tokens |
| Input price / 1M | $4.00via Anthropic | $1.80via Together AI |
| Output price / 1M | $20.00via Anthropic | $1.80via Together AI |
| Providers | 1 | 2 |
| License | proprietary | apache-2.0 |
| Input modalities | code, image, text | code, text |
| Capabilities | chat, completion, function-calling, vision, code-generation, reasoning | chat, completion, function-calling, 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.
| Benchmark | Claude Opus 5.5 | GPT-OSS 120B |
|---|---|---|
| Artificial Analysis Intelligence Index | 58Artificial Analysis · Independent | — |
| AutomationBench | 40%Anthropic · Vendor-reported | — |
| Chartography | 89%Anthropic · Vendor-reported | — |
| CursorBench 4.0 | 57.8%Anthropic · Vendor-reported |
| — |
| FrontierCode Main 1.1 | 54.4%Anthropic · Vendor-reported | — |
|---|
| GDPval-AA 2.1 | 1,846Anthropic · Vendor-reported | — |
|---|
| Humanity's Last Exam | 67.7%Anthropic · Vendor-reported | — |
|---|
| OSWorld 2.1 | 81.8%Anthropic · Vendor-reported | — |
|---|
| Terminal-Bench 4.0 | 66.4%Anthropic · Vendor-reported | — |
|---|
| Terminal-Bench-Science 0.1 | 58.7%Anthropic · Vendor-reported | — |
|---|