isitsota / categories / General LLM
General LLM · Oct 13, 2026
Who is SOTA in General LLM?
Gemini 2.5 Pro
Best publicly available general-purpose language model, judged from independent preference and contamination-resistant composite evidence. As of Oct 13, 2026, Gemini 2.5 Pro holds General LLM. Gemini 2.5 Pro is SOTA in General LLM since 2026-01-27. No eligible model is credibly ahead on the…
Standings · overall
The board
| # | Model | State | Confidence |
|---|---|---|---|
| 1 | GGemini 2.5 Pro Exp 03.25 Google DeepMind | Near-SOTA | medium |
| 1 | GGemini 4 Argon Google DeepMind | Not SOTA · #1 | medium |
| 1 | GGemini 2.5 Pro Google DeepMind | SOTA | high |
| 3 | AClaude 3.7 Sonnet Anthropic | Near-SOTA | medium |
| 4 | AClaude Opus 5.5 Anthropic | Not SOTA · #4 | medium |
| 5 | OO3 Mini OpenAI | Not SOTA · #5 | medium |
| 6 | OO1 OpenAI | Not SOTA · #6 | medium |
| 7 | AClaude Opus 4.6 Anthropic | Not SOTA · #7 | medium |
| 8 | QQwq 32B Alibaba / Qwen | Not SOTA · #8 | medium |
| 9 | DSDeepSeek R1 DeepSeek | Not SOTA · #9 | medium |
| 10 | AClaude Fable 5 Anthropic | Not SOTA · #10 | medium |
| 11 | OGPT-4.5 Preview OpenAI | Not SOTA · #11 | medium |
| 12 | GGemini 2.0 Flash Thinking Exp 01.21 Google DeepMind | Not SOTA · #12 | medium |
Evidence recipe
What can move this crown
- LMArena Text (style-controlled, overall) — primary, weight 1
- Artificial Analysis Intelligence Index — primary, weight 1
- LiveBench — secondary, weight 0.45