Hard reasoning and expert-question performance. Saturated exams drop out of the crown automatically. As of Oct 14, 2026, Gemini 4 Argon & Claude Opus 5.5 are tied for state of the art in Reasoning (since Oct 2, 2026; sources LMArena Text…
| # | Model | State | Confidence |
|---|---|---|---|
| 1 | GGemini 4 Argon Google DeepMind | Co-SOTA · Reasoning | medium |
| 1 | AClaude Opus 5.5 Anthropic | Co-SOTA · Reasoning | medium |
| 2 | AClaude Opus 4.6 Anthropic | Near-SOTA · Reasoning | medium |
| 3 | AClaude Fable 5 Anthropic | Near-SOTA · Reasoning | medium |
| 4 | AClaude Opus 4.7 Anthropic | Near-SOTA · Reasoning | medium |
| 1 | MMuse Wonder Meta | Pending · Reasoning | low |
| 5 | AClaude Fable 5.1 Anthropic | Was SOTA · Reasoning | medium |
| 6 | GGemini 3.8 Flash Google DeepMind | #6 in Reasoning | medium |
| 7 | KKimi K3 Moonshot AI | #7 in Reasoning | medium |
| 8 | MMuse Spark 1.3 Meta | #8 in Reasoning | medium |
| 9 | AClaude Opus 5 Anthropic | Was SOTA · Reasoning | medium |
| 10 | AClaude Opus 4.8 Anthropic | #10 in Reasoning | medium |
| 11 | MMuse Spark 1.2 Meta | #11 in Reasoning | medium |
| 12 | OGPT-5.6 Sol OpenAI | #12 in Reasoning | medium |
| 13 | MMuse Spark 1.1 Meta | #13 in Reasoning | medium |
Badges for the leaders
[](https://isitsota.com/m/gemini-4-argon)
<a href="https://isitsota.com/m/gemini-4-argon"><img alt="CO-SOTA · Reasoning · Oct 2026" src="https://isitsota.com/badge/gemini-4-argon/reasoning.svg" height="28"></a>
[](https://isitsota.com/m/claude-opus-5-5)
<a href="https://isitsota.com/m/claude-opus-5-5"><img alt="CO-SOTA · Reasoning · Oct 2026" src="https://isitsota.com/badge/claude-opus-5-5/reasoning.svg" height="28"></a>
Best page and recent changes
- Reasoning (best per dollar): DeepSeek V4.1 Flash and DeepSeek V4 Flash and Gemini 3.8 Flash and Gemini 4 Argon and GLM 5.3 and GLM 5.3 Flash and Hy3 and Mimo V2.6 Flash and Mimo V2.6 Pro are co-SOTA
- Reasoning: Kimi K3 and Mimo V2.6 Pro are co-SOTA
- Reasoning: Gemma 4 31B and Qwen3 8 27B and Gemma 4 26B A4b are co-SOTA
What can move this crown
- Humanity's Last Exam — primary, weight 1
- GPQA Diamond — primary, weight 1
- LMArena Text (style-controlled, hard prompts) — primary, weight 1
- LiveBench — secondary, weight 0.35
Who is SOTA in Reasoning?
As of Oct 14, 2026, Gemini 4 Argon & Claude Opus 5.5 are tied for state of the art in Reasoning (since Oct 2, 2026; sources LMArena Text (style-controlled, hard prompts); methodology v1.0).
Since when is the Reasoning crown current?
The current crown in Reasoning has held since Oct 2, 2026.