Claude vs GPT
Anthropic's Claude and OpenAI's GPT, compared through their current models on the Respan Index. The strongest Claude model today is Claude Fable 5.2 (#1 on the Respan Index, 80.8); the strongest GPT model is GPT-6.2 Astra (#5, 74.8). Claude's best models lead in coding, agents, reasoning, knowledge and human preference.
Flagship vs flagship
The highest ranked Claude and GPT models on the Respan Index.
| Spec | Claude Fable 5.2 | GPT-6.2 Astra |
|---|---|---|
| Respan Index | 80.8 (#1) | 74.8 (#5) |
| Blended price per 1M | $16 | $16 |
| Context window | - | - |
| Input / output per 1M | $8 / $40 | $8 / $40 |
Best in each category
Each family's top scorer per category, scored 0 to 100, and how far ahead the winner is. Leads under a point are close to even.
| Category | Claude | GPT |
|---|---|---|
| Coding | 78.8Claude Sonnet 5.5 | 65.8GPT-6.2 Sol |
| Agents | 85.3Claude Fable 5.2 | 83.6GPT-6.2 Astra |
| Reasoning | 90.2Claude Fable 5.2 | 90.0GPT-6.2 Astra |
| Knowledge & language | 94.0Claude Fable 5.2 | 78.6GPT-6.2 Astra |
| Human preference | 61.7Claude Fable 5.2 | 60.2GPT-6.2 Astra |
Both lineups, ranked
The top 6 Claude and GPT models in Respan Index order, with blended list price per 1M tokens.
| Rank | Model | Index | Price |
|---|---|---|---|
| #1 | Claude Fable 5.2 | 80.8 | $16/M |
| #4 | Claude Opus 5.5 | 76.0 | $8/M |
| #5 | GPT-6.2 Astra | 74.8 | $16/M |
| #6 | Claude Sonnet 5.5 | 73.4 | $4/M |
| #7 | Claude Fable 5.1 | 72.3 | $20/M |
| #7 | GPT-6 Astra | 72.3 | $20/M |
| #12 | GPT-6.1 Sol | 69.7 | $4/M |
| #14 | GPT-6.1 Terra | 69.1 | $2/M |
| #15 | GPT-6.2 Sol | 68.0 | $4/M |
| #16 | Claude Opus 5 | 67.0 | $10/M |
| #18 | Claude Fable 5 | 63.9 | $20/M |
| #19 | GPT-6 Sol | 63.0 | $4/M |
The cheapest ranked Claude model is Claude Haiku 5.5 at $0.2 per 1M tokens blended; the cheapest GPT model is gpt-oss-20b at $0.036.
FAQ
Is Claude better than GPT?
The strongest Claude model today is Claude Fable 5.2 (#1 on the Respan Index, 80.8); the strongest GPT model is GPT-6.2 Astra (#5, 74.8). Claude's best models lead in coding, agents, reasoning, knowledge and human preference.
Is Claude or GPT better for coding?
On the Respan Index coding score, Claude's best is Claude Sonnet 5.5 at 78.8 and GPT's best is GPT-6.2 Sol at 65.8. The coding score blends SWE-bench, Terminal-Bench and other coding benchmarks.
Which is cheaper, Claude or GPT?
The cheapest ranked Claude model is Claude Haiku 5.5 at $0.2 per 1M tokens blended; the cheapest GPT model is gpt-oss-20b at $0.036.
What are the best Claude and GPT models right now?
Claude Fable 5.2 for Claude and GPT-6.2 Astra for GPT, ranked #1 and #5 on the Respan Index, which blends public benchmarks across coding, agents, reasoning, knowledge and human preference.
Is ChatGPT the same as GPT?
ChatGPT is OpenAI's chat app, and it runs OpenAI's GPT models. This page compares the models themselves, as developers reach them through the API, not the apps.