Claude Opus 4.8 vs GPT-5.5
Anthropic vs OpenAI — benchmarks, pricing, and capabilities side by side.
- •GPT-5.5 has the higher intelligence index (74.6 vs 73.1)
- •GPT-5.5 is cheaper ($5.00 vs $6.30 per 1M input)
- •GPT-5.5 is faster
| Claude Opus 4.8 | GPT-5.5 | |
|---|---|---|
| Intelligence index | 73.1 | 74.6 |
| Developer | Anthropic | OpenAI |
| Type | LLM | LLM |
| Access | — | API only |
| Context window | — | 1,050,000 tokens |
| Input price | $6.30 / 1M | $5.00 / 1M |
| Output price | $25.00 / 1M | $30.00 / 1M |
| Speed | 66 tok/s | 67 tok/s |
| Released | May 28, 2026 | April 23, 2026 |
| Parameters | — | — |
| Input modalities | — | Text, Image |
| Output modalities | — | Text |
Shared benchmarks
Claude Opus 4.8
GPT-5.5
AA-LCR
67.7
74.3
GPQA Diamond
92
93.5
Humanity’s Last Exam
45.7
44.3
SciCode
53.5
56.1
Terminal-Bench
58.3
60.6
τ²-bench
94.4
93.9