Compare, 2 models
Side by side.
Claude Haiku 5.5 and GPT-5.2 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 | Claude Haiku 5.5Anthropic | GPT-5.2OpenAI |
|---|---|---|
| Lab | Anthropic | OpenAI |
| Type | Language | Language |
| Released | Oct 7, 2026 | Dec 11, 2025 |
| Input price$ per 1M tokens | $0.10 | $1.75 |
| Output price$ per 1M tokens | $0.50 | $14.00 |
| Blended price3 input tokens per output | $0.20 | $4.81 |
| Contexttokens | 1M | 400K |
| Open weights | No | No |
| Output speedTok / s | 239 | n/a |
Benchmarks
Every board where at least two of these models have a published score. Each score links to its source.
| Board | Claude Haiku 5.5Anthropic | GPT-5.2OpenAI |
|---|---|---|
| Humanity's Last ExamReasoning and knowledge, higher is better | 30.1% | 27.8% |
| ARC-AGI-2Reasoning and knowledge, higher is better | 61.3%xhigh setting | 52.9%xhigh setting |
n/a means the board has not published a score for that model.