isitsota / categories / Reasoning
Reasoning / knowledge · Oct 13, 2026
Who is SOTA in Reasoning?
GPT-6 Astra & Gemini 4 Argon & Claude Opus 5.5
Hard reasoning and expert-question performance. Saturated exams drop out of the crown automatically. As of Oct 13, 2026, GPT-6 Astra & Gemini 4 Argon & Claude Opus 5.5 share Reasoning. GPT-6 Astra is co-SOTA in Reasoning with low confidence because…
Standings · overall
The board
| # | Model | State | Confidence |
|---|---|---|---|
| 1 | OGPT-6 Astra OpenAI | Co-SOTA | low |
| 1 | GGemini 4 Argon Google DeepMind | Co-SOTA | low |
| 3 | AClaude 3.7 Sonnet Anthropic | Near-SOTA | medium |
| 4 | GGemini 3.1 Pro Preview Google DeepMind | Was SOTA | medium |
| 5 | AClaude Opus 5.5 Anthropic | Co-SOTA | low |
| 6 | OO3 Mini OpenAI | Not SOTA · #6 | medium |
| 7 | OGPT-5.4 Pro OpenAI | Was SOTA | medium |
| 8 | MMuse Spark Meta | Was SOTA | medium |
| 9 | GGemini 3 Pro Preview Google DeepMind | Was SOTA | medium |
| 10 | OGPT-5.4 OpenAI | Was SOTA | medium |
| 11 | QQwq 32B Alibaba / Qwen | Not SOTA · #11 | medium |
| 12 | AClaude Opus 4.6 Anthropic | Near-SOTA | medium |
| 14 | AClaude Fable 5.1 Anthropic | Near-SOTA | medium |
| 15 | AClaude Fable 5 Anthropic | Near-SOTA | medium |
| 15 | OGPT-5 Pro OpenAI | Was SOTA | medium |
Evidence recipe
What can move this crown
- Humanity's Last Exam — primary, weight 1
- GPQA Diamond — primary, weight 1 (display only, cannot crown)
- LMArena Text (style-controlled, hard prompts) — primary, weight 1
- LiveBench — secondary, weight 0.35