Updated Jun 6, 2026

llmleaderboard.in

Largest Context Window LLM in 2026

Maximum tokens per request — critical for long documents, full codebases, and agent traces. Effective usable context may be lower than advertised.

Llama 4 Scout advertises 10M tokens — the largest on our leaderboard. Gemini 3 Pro offers 2M; many GPT-5 and Claude variants support 1M tokens for enterprise RAG and repo-wide analysis.

LLMs with the largest context windows
#ModelProviderContextGPQACost
1Llama 4 ScoutMeta10M76.5%Open
2Gemini 3 ProGoogle2M92.1%$3.5 / $10.5
3Claude Mythos PreviewAnthropic1M94.6%Limited
4Claude Opus 4.8Anthropic1M94.4%$6 / $30
5Claude Opus 4.6Anthropic1M91.2%$5 / $25
6Claude Sonnet 4.6Anthropic1M88.5%$3 / $15
7GPT-5.5OpenAI1M93.6%$5 / $30
8GPT-5.5 ProOpenAI1M94.2%$30 / $180
9MAI-Image-2.5Microsoft1M$5 / $47
10MAI-Image-2.5-FlashMicrosoft1M$1.75 / $19.50
11GPT-5.4OpenAI1M92.8%$5 / $30
12GPT-5.4 ProOpenAI1M94.5%$30 / $180

When context size matters

Large context helps ingest entire PDFs, monorepos, or long chat histories in one shot. For many apps, RAG with a smaller window plus retrieval is cheaper and more reliable than stuffing everything into the prompt.

See all 45 models with live benchmarks, speed, and pricing.

Open full LLM leaderboard →