⌕Is ___ SOTA?
isitsota / categories / Long context
Long context · Oct 13, 2026
Who is SOTA in Long context?
O3 & Kimi K2 5 & GPT-5 Mini & GPT-5 Nano

Usable long context, not a needle-in-a-haystack demo. Fiction.liveBench at 120k tokens plus longer-query preference. As of Oct 13, 2026, O3 & Kimi K2 5 & GPT-5 Mini & GPT-5 Nano holds Long context. On the cost-quality frontier for Long context: nothing scores better for…

OverallOpen weights≤ 32BBest per $
Standings · pareto

The board

History →
#ModelStateConfidenceWhy
1GGemini 4 Argon
Google DeepMind		Near-SOTAmediumNot on the Long context cost-quality frontier.
1OO3
OpenAI		ParetomediumOn the cost-quality frontier for Long context: nothing scores better for less than $3.50 per 1M blended tokens.
3OGPT-5
OpenAI		Not SOTA · #3mediumNot on the Long context cost-quality frontier.
6OO3 Pro
OpenAI		Not SOTA · #6mediumNot on the Long context cost-quality frontier.
7AClaude Opus 5.5
Anthropic		Not SOTA · #7mediumNot on the Long context cost-quality frontier.
9KKimi K2 5
Moonshot AI		ParetomediumOn the cost-quality frontier for Long context: nothing scores better for less than $1.00 per 1M blended tokens.
13AClaude Opus 4.6
Anthropic		Not SOTA · #13mediumNot on the Long context cost-quality frontier.
18AClaude Fable 5
Anthropic		Not SOTA · #18mediumNot on the Long context cost-quality frontier.
20AClaude Opus 4.7
Anthropic		Not SOTA · #20mediumNot on the Long context cost-quality frontier.
21OGPT-4.1
OpenAI		Not SOTA · #21mediumNot on the Long context cost-quality frontier.
21OGPT-5 Mini
OpenAI		ParetomediumOn the cost-quality frontier for Long context: nothing scores better for less than $0.69 per 1M blended tokens.
21OO4 Mini
OpenAI		Not SOTA · #21mediumNot on the Long context cost-quality frontier.
26MIMinimax M1
minimax		Not SOTA · #26mediumNot on the Long context cost-quality frontier.
28GGemini 3.8 Flash
Google DeepMind		Not SOTA · #28mediumNot on the Long context cost-quality frontier.
29OO1
OpenAI		Not SOTA · #29mediumNot on the Long context cost-quality frontier.
Pareto

Quality against blended price

Gemini 4 ArgonO3GPT-5O3 ProClaude Opus 5.5Kimi K2 5Claude Opus 4.6Claude Fable 5Claude Opus 4.7GPT-4.1GPT-5 MiniO4 Mini
Evidence recipe

What can move this crown