Model comparison
Claude Sonnet 4.6 vs GPT-5.5
A spec-by-spec comparison of Claude Sonnet 4.6 and GPT-5.5: pricing, context window, capabilities, and independently sourced benchmarks.
Head-to-head
- Claude Sonnet 4.6 costs 1.7x less per input token than GPT-5.5 ($3.00/MTok vs $5.00/MTok).
- GPT-5.5 has a 1.1x larger context window than Claude Sonnet 4.6 (1,050,000 tokens vs 1,000,000 tokens).
| Spec | Claude Sonnet 4.6 | GPT-5.5 |
|---|---|---|
| Provider | anthropic | openai |
| Family | Claude Sonnet | GPT-5.5 |
| Status | legacy | current |
| Release date | 2026-02-17 | — |
| Knowledge cutoff | 2025-08 | 2025-12-01 |
| Context window | 1,000,000 tokens | 1,050,000 tokens |
| Max output tokens | 128,000 tokens | 128,000 tokens |
| Input price | $3.00/MTok | $5.00/MTok |
| Output price | $15.00/MTok | $30.00/MTok |
| Cached input price | $0.30/MTok | $0.50/MTok |
| Vision | Yes | Yes |
| Tool use | Yes | Yes |
| Extended thinking | Yes | Yes |
| Streaming | — | Yes |
Benchmarks
Independently sourced scores
A dash means that model has no publicly sourced score for that benchmark, not a zero.
| Benchmark | Claude Sonnet 4.6 | GPT-5.5 |
|---|---|---|
| GPQA Diamond (xhigh reasoning effort) | — | 93.5% |
Claude Sonnet 4.6
Strengths- Uses the older Claude tokenizer, so the same text bills ~30% fewer tokens than on Sonnet 5.
- Carries the full 1M-token context window at standard pricing.
- Superseded by Claude Sonnet 5, which is cheaper until 2026-08-31 and the same price after.
- Tool-use system prompt overhead is 497 tokens on auto against 354 on Sonnet 5.
GPT-5.5
Strengths- Priced identically to GPT-5.6 Sol at $5.00/$30.00 per MTok.
- Audio and video are not accepted; image input and text output only.
- Prompts over 272K input tokens bill at 2x input and 1.5x output for the whole session.
- Knowledge cutoff of 2025-12-01 is 2.5 months behind the GPT-5.6 family.
Not sure which one to use?
Flaibo is a daily AI orientation hub: a 12-week path and a prompt vault, with Free and Professional plans. Build the habit, not just the comparison.
Start your AI path