How are flagship models ranked?

Each model is scored on weighted, normalized metrics (pricing, capability, and benchmark data), then adjusted for data confidence and freshness. Sources are listed on every model page.

How fresh is this data?

Data is verified against named sources and flagged when older than 45 days. The last verification date is shown on each page.

Flagship Models

The most capable general-purpose models from each provider.

9 models · Updated Jul 12, 2026

#		provider	model category
2	Claude Opus 4.8	Anthropic	—	49.7
3	GPT-5.5	OpenAI	—	46.5
4	DeepSeek V4 Pro	DeepSeek	—	45.9
5	Gemini 3.1 Pro Preview	Google	—	45.1
8	Kimi K2.6	Moonshot AI	—	29.1
9▲1	GPT-5.5 Pro	OpenAI	—	28.3
10▲1	Qwen3.7 Max	Alibaba	—	28.1
11▲1	Grok 4.20 (Reasoning)	xAI	—	28.0
14▲1	Mistral Large 3	Mistral	—	19.3

Ranking combines weighted, normalized metrics with confidence and freshness adjustments. Missing data lowers a score rather than being ignored.

Popular comparisons

Claude Opus 4.8 vs GPT-5.5
Claude Opus 4.8 vs DeepSeek V4 Pro
GPT-5.5 vs DeepSeek V4 Pro

Related model categories

Coding Models
Efficient Models

Frequently asked questions

How are flagship models ranked?: Each model is scored on weighted, normalized metrics (pricing, capability, and benchmark data), then adjusted for data confidence and freshness. Sources are listed on every model page.
How fresh is this data?: Data is verified against named sources and flagged when older than 45 days. The last verification date is shown on each page.