isitsota / categories / Long context
Long context · Oct 13, 2026
Who is SOTA in Long context?
O3 & Grok 4 0709 & GPT-5
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 & Grok 4 0709 & GPT-5 share Long context. O3 is tied for SOTA in Long context with Grok 4 0709, GPT-5, within the margin of error,…
Standings · overall
The board
| # | Model | State | Confidence |
|---|---|---|---|
| 1 | OO3 OpenAI | Co-SOTA | high |
| 1 | GGemini 4 Argon Google DeepMind | Pending | low |
| 3 | xGrok 4 0709 xAI | Co-SOTA | high |
| 3 | OGPT-5 OpenAI | Co-SOTA | high |
| 5 | AClaude Opus 5.5 Anthropic | Not SOTA · #5 | medium |
| 6 | GGemini 2.5 Pro Exp 03.25 Google DeepMind | Was SOTA | medium |
| 7 | OO3 Pro OpenAI | Not SOTA · #7 | medium |
| 8 | AClaude Opus 4.6 Anthropic | Not SOTA · #8 | medium |
| 9 | GGemini 2.5 Pro Preview 06.05 Google DeepMind | Not SOTA · #9 | medium |
| 10 | KKimi K2 5 Moonshot AI | Not SOTA · #10 | medium |
| 11 | AClaude Fable 5 Anthropic | Not SOTA · #11 | medium |
| 11 | xGrok 4 Fast xAI | Not SOTA · #11 | medium |
| 16 | OChatGPT 4O 01.29 2025 OpenAI | Was SOTA | medium |
| 19 | GGemini 2.0 Flash 001 Google DeepMind | Was SOTA | medium |
| 25 | OO1 OpenAI | Was SOTA | medium |
Evidence recipe
What can move this crown
- Fiction.liveBench 120k — primary, weight 1
- LMArena Text (style-controlled, longer query) — primary, weight 0.7