Claude vs ChatGPT

A live, data-driven comparison of Claude and ChatGPT — top models from each brand, 6+ benchmarks, API pricing across every provider, and how each brand's models have evolved over time.

Get our weekly newsletter on pricing changes, new releases, and tools.

Claude vs ChatGPT: the short answer

ChatGPT leads on coding benchmarks (GPT-6 Astra), ChatGPT has the cheapest API option (GPT-OSS-20b at $0.02/M input). Full benchmark, pricing, and capability breakdown below.

Cheapest API
GPT-OSS-20b
$0.02 / M in
Best for coding
GPT-6 Astra
76.2 coding
Biggest context
GPT-6.1 Terra
1050K tokens
Newest model
GPT-6.1 Terra
2026-10-26

Benchmarks: Claude vs ChatGPT at their best

Each bar is the best score any Claude or ChatGPT model achieves on that benchmark. Only benchmarks where both brands have a score are shown.

ClaudeChatGPT

🧠 Intelligence & Knowledge

Intelligence IndexClaude Opus 5.5 vs GPT-6.1 Sol
59.1
54.6
GPQAClaude Fable 5.1 vs GPT-5.6 Terra
93.7
92.5
HLEClaude Opus 5.5 vs GPT-6.1 Sol
61.4
52.9

💻 Coding

AiderClaude 3.5 Sonnet vs GPT-5
84.2
88.0
SciCodeClaude Opus 5.5 vs GPT-6 Sol
66.9
57.6

🤖 Agentic & Tools

LCRClaude Fable 5.1 vs GPT-6 Sol
85.3
83.7

Model releases over time

Every Claude and ChatGPT model with a known release date, on one timeline — the release cadence of each brand at a glance.

Model Release Timeline

24 releases
Mar 2026
$0.38 / $2.25
Mar 2026
$0.10 / $0.63
Apr 2026
$5.00 / $25.00
Apr 2026
$5.00 / $30.00
Apr 2026
$30.00 / $180.00
May 2026
$5.00 / $30.00
May 2026
$5.00 / $25.00
May 2026
$10.00 / $50.00
Jun 2026
$10.00 / $50.00
Jun 2026
$2.00 / $10.00
Jul 2026
$2.00 / $10.00
Jul 2026
$4.00 / $20.00
Jul 2026
$2.00 / $12.00
Jul 2026
$2.00 / $12.00
Jul 2026
$0.20 / $1.20
Jul 2026
$0.10 / $0.60
Jul 2026
$5.00 / $25.00
Jul 2026
$10.00 / $50.00
Sep 2026
$10.00 / $50.00
Sep 2026
$10.00 / $50.00
Sep 2026
$5.00 / $25.00
Sep 2026
$2.00 / $10.00
Oct 2026
$0.10 / $0.50
Oct 2026
$1.00 / $5.00
Spacing represents time between releases
Mar 2026→Oct 2026

Pricing & Models

Claude
ModelInput /MOutput /MContextCoding
Claude Haiku 5.5$0.10$0.501000K—
Claude Sonnet 5.5$2.00$10.001000K—
Claude Fable 5.1$10.00$50.001000K—
Claude Opus 5 Fast$10.00$50.001000K—
Claude Opus 5$5.00$25.001000K—
Claude Sonnet 5$2.00$10.001000K—
Claude Fable 5$10.00$50.001000K—
Claude Opus 4.8 Fast$10.00$50.001000K—
ChatGPT
ModelInput /MOutput /MContextCoding
GPT-6.1 Terra$1.00$5.001050K—
GPT-6 Astra$5.00$25.001050K76.2
GPT-6 Astra Pro$10.00$50.001050K—
GPT-5.6 Luna Pro$0.10$0.601050K—
GPT-5.6 Luna$0.20$1.201050K—
GPT-5.6 Terra Pro$2.00$12.001050K—
GPT-5.6 Terra$2.00$12.001050K—
GPT-5.6 Sol Pro$4.00$20.001050K—

Prices are per 1M tokens, lowest available across API providers. Showing the 8 most recent models per brand.

Frequently Asked Questions

Neither wins outright — it depends on the task. GPT-6 Astra currently posts the top coding benchmark across both brands. Use the benchmark and pricing breakdown above to pick the right model for your workload.
Claude's cheapest model starts at $0.10/M input tokens and ChatGPT's starts at $0.02/M. ChatGPT is the cheaper option at the low end. See per-provider API pricing above for exact costs.
Across the latest models from both brands, GPT-6 Astra has the highest coding benchmark score (76.2). The Coding section above breaks down LiveCodeBench, Aider, SWE-bench, and TerminalBench.
The largest context window across these brands is GPT-6.1 Terra at 1050K tokens. Per-model context windows are in the pricing tables above.
If you're building an app or calling models programmatically, the API (priced per token above) is usually cheaper for bursty or low-volume use. A monthly chat subscription can be better for heavy daily interactive use. Compare your expected token volume against the per-token prices above.
Yes — many teams route different tasks to different models. Several API providers (e.g. OpenRouter) expose both Claude and ChatGPT models behind one API, and the per-provider pricing above shows where each is cheapest.