Anthropic's Claude and OpenAI's GPT, compared through their current models on the Respan Index. The strongest Claude model today is Claude Opus 5.5 (#1 on the Respan Index, 72.4); the strongest GPT model is GPT-6 Astra (#2, 70.5). Claude's best models lead in coding, agents and human preference; GPT's lead in reasoning and knowledge.
| Category | Claude | GPT |
|---|---|---|
| coding | Claude Opus 5.5 72.8 | GPT-6 Astra 61.8 |
| agents | Claude Sonnet 5.5 78.1 | GPT-6 Astra 77.0 |
| reasoning | Claude Opus 5.5 75.5 | GPT-6.1 Sol 78.6 |
| knowledge | Claude Fable 5 72.4 | GPT-6 Astra 75.8 |
| human preference | Claude Opus 5.5 60.6 | GPT-6 Astra |
Each family's highest Respan Index category score; the higher one is bold. * Estimated: no published scores in that category. How the Respan Index works
Respan Index rank and score, blended list price per 1M tokens.
Respan Index rank and score, blended list price per 1M tokens.
The cheapest ranked Claude model is Claude Haiku 4.5 at $2 per 1M tokens blended; the cheapest GPT model is GPT-5 nano at $0.138.