What's new

Context Window Comparison

54 LLMs ranked by context window size. Larger context means more text can be processed in a single conversation — crucial for analysing long documents, codebases, and research papers.

14

1M+ tokens

18

200K–999K

21

32K–199K

1

<32K tokens

Full Table

# Model Context Quality
1 Llama 4 Scout OSS Meta 10M 79.0
2 Gemini 2.5 Pro Google 1.0M 83.0
3 Gemini 2.0 Flash Google 1.0M 81.0
4 Gemini 2.5 Flash Google 1.0M 78.0
5 Llama 4 Maverick OSS Meta 1.0M 76.0
6 Gemini 2.0 Flash Lite Google 1.0M 75.0
7 Gemini 2.5 Flash Lite Google 1.0M 74.0
8 GPT-4.1 OpenAI 1.0M 77.0
9 GPT-4.1 Mini OpenAI 1.0M 75.0
10 GPT-4.1 Nano OpenAI 1.0M 75.0
11 Claude Opus 4.6 Anthropic 1M 89.0
12 Claude Sonnet 4.6 Anthropic 1M 86.0
13 Claude Sonnet 4 Anthropic 1M 79.0
14 Claude Sonnet 4.5 Anthropic 1M 79.0
15 GPT-5.2 Pro OpenAI 400K 93.0
16 GPT-5 Pro OpenAI 400K 90.0
17 GPT-5.2 OpenAI 400K 90.0
18 GPT-5 OpenAI 400K 87.0
19 GPT-5 Nano OpenAI 400K 78.0
20 Nova Pro 1.0 Amazon 300K 78.0
21 Nova Lite 1.0 Amazon 300K 72.0
22 Qwen3 Max OSS Alibaba 262.1K 85.0
23 Command A OSS Cohere 256K 80.0
24 O4 Mini OpenAI 200K 90.0
25 O3 OpenAI 200K 88.0
26 O3 Pro OpenAI 200K 88.0
27 Claude Opus 4.5 Anthropic 200K 86.0
28 Claude Opus 4 Anthropic 200K 84.0
29 o1 OpenAI 200K 84.0
30 o3 Mini OpenAI 200K 84.0
31 Claude 3.5 Haiku Anthropic 200K 76.0
32 Claude Haiku 4.5 Anthropic 200K 76.0
33 DeepSeek R1 OSS DeepSeek 163.8K 85.0
34 R1 0528 OSS DeepSeek 163.8K 83.0
35 DeepSeek V3.2 OSS DeepSeek 163.8K 77.0
36 Qwen3 235B A22B OSS Alibaba 131.1K 87.0
37 Llama 3.1 70B Instruct OSS Meta 131.1K 77.0
38 DeepSeek V3 OSS DeepSeek 131.1K 76.0
39 Mistral Nemo OSS Mistral 131.1K 72.0
40 Llama 3.3 70B Instruct OSS Meta 131.1K 71.0
41 Qwen2.5 72B Instruct OSS Alibaba 131.1K 71.0
42 Llama 3.1 8B Instruct OSS Meta 131.1K 68.0
43 Qwen2.5 Coder 32B Instruct OSS Alibaba 128K 82.0
44 Command R+ (08-2024) OSS Cohere 128K 79.0
45 GPT-4o (2024-05-13) OpenAI 128K 75.0
46 GPT-4o-mini OpenAI 128K 74.0
47 Command R (08-2024) OSS Cohere 128K 73.0
48 Mistral Large OSS Mistral 128K 73.0
49 Mistral Small 3.1 24B OSS Mistral 128K 72.0
50 Nova Micro 1.0 Amazon 128K 68.0
51 Command R7B (12-2024) OSS Cohere 128K 65.0
52 Sonar Perplexity 127.1K 74.0
53 Reka Flash 3 Reka 65.5K 74.0
54 Phi 4 OSS Microsoft 16.4K 74.0

What is a context window?

The context window is the maximum amount of text a model can process in a single request — including both your input and its response. It's measured in tokens (roughly 0.75 words per token).

32K tokens

~24,000 words / ~96 pages. Enough for a long article or short story.

200K tokens

~150,000 words / ~600 pages. Enough for a full novel or large codebase.

1M+ tokens

~750,000+ words / ~3,000+ pages. Entire book series, repos, or document collections.