Compare, 2 models
Side by side.
Gemini 3 Deep Think and GPT-5.5 on every board at least two of them share. Blue marks the best in each row.
Specs
List prices, context and published output speed. Blue marks the best in each row.
| Spec | Gemini 3 Deep ThinkGoogle | GPT-5.5OpenAI |
|---|---|---|
| Lab | OpenAI | |
| Type | Language | Language |
| Released | Feb 12, 2026 | Apr 23, 2026 |
| Input price$ per 1M tokens | n/a | $5.00 |
| Output price$ per 1M tokens | n/a | $30.00 |
| Blended price3 input tokens per output | n/a | $11.25 |
| Contexttokens | n/a | 1.05M |
| Open weights | No | No |
Benchmarks
Every board where at least two of these models have a published score. Each score links to its source.
| Board | Gemini 3 Deep ThinkGoogle | GPT-5.5OpenAI |
|---|---|---|
| ARC-AGI-2Reasoning and knowledge, higher is better | 84.6% | 85.0%xhigh setting |
n/a means the board has not published a score for that model.