Is Grok 4.20 Multi Agent Beta state of the art?#45Best current rank: #45 in General LLM, as of Nov 22, 2026.
As of Nov 22, 2026, Grok 4.20 Multi Agent Beta is ranked #45 in General LLM (since Nov 22, 2026; sources LMArena Text (style-controlled, overall); methodology v1.0). Ranked #45 in General LLM.
Facts and scores
Grok 4.20 Multi Agent Beta is a closed-weights text model from xAI, listed on LMArena since Oct 19, 2026; no public parameter count and no public price.
How it scores
- On LMArena Text (style-controlled, overall) it scores 1471 (CI 1467–1475), #55 of 257 (top 22%); 56 behind Gemini 4 Carbon; Grok 4.20 Beta 0309 Reasoning is 1 above and Grok 4.20 Multi Agent Beta 0309 is 1 below.
- On LMArena Text factuality it scores 1458 (CI 1455–1461), #53 of 215 (top 25%); 64 behind Gemini 4 Carbon; level with GPT-5.1 above and Grok 4.20 Multi Agent Beta 0309 is 1 below.
- On LMArena Text (style-controlled, hard prompts) it scores 1484 (CI 1480–1489), #67 of 263 (top 26%); 63 behind Gemini 4 Carbon; GPT-6.2 Astra is 1 above and level with GPT-6 Sol below.
History
First result on isitsota: Nov 19, 2026. Best overall rank so far: #45 in General LLM, first held Nov 22, 2026.
Evidence
| Source | Score | Date | Type | Receipt |
|---|---|---|---|---|
| LMArena Text (style-controlled, overall) Grok 4.20 Multi-Agent Beta (0309) | 1471 1467–1475 | 2026-11-19 | INDEP. | snap_280a9b5ca493 |
| LMArena Text (style-controlled, hard prompts) Grok 4.20 Multi-Agent Beta (0309) | 1484 1480–1489 | 2026-11-19 | INDEP. | snap_280a9b5ca493 |
| LMArena Text (style-controlled, math) Grok 4.20 Multi-Agent Beta (0309) | 1454 1444–1465 | 2026-11-19 | INDEP. | snap_280a9b5ca493 |
| LMArena Text (style-controlled, coding) Grok 4.20 Multi-Agent Beta (0309) | 1508 1503–1514 | 2026-11-19 | INDEP. | snap_280a9b5ca493 |
| LMArena Text (style-controlled, longer query) Grok 4.20 Multi-Agent Beta (0309) | 1458 1453–1464 | 2026-11-19 | INDEP. | snap_280a9b5ca493 |
| LMArena Vision (style-controlled) Grok 4.20 Multi-Agent Beta (0309) | 1251 1245–1257 | 2026-11-19 | INDEP. | snap_71563b13a9cc |
| LMArena Text factuality Grok 4.20 Multi-Agent Beta (0309) | 1458 1455–1461 | 2026-11-19 | INDEP. | snap_275d95909246 |
Where it sits in the succession
Crown intervals for this model are still empty.
Where it is not the crown
| Category | This model | Rank | Leader |
|---|---|---|---|
| General LLM | #45 in this category | #45 | Gemini 4 Carbon |
| Reasoning | #55 in this category | #55 | Gemini 4 Carbon |
| Math | Not enough data | — | GPT-6 Astra |
| Coding | Not enough data | — | Claude Sonnet 5.5 |
| Long context | #71 in this category | #71 | Gemini 4 Argon |
| Vision | Not enough data | — | — |
| Factuality | #49 in this category | #49 | Gemini 4 Carbon |
Related pages
- General LLM
- Reasoning
- Math
- Coding
- Long context
- Vision
- Factuality
- LMArena Vision (style-controlled)
- LMArena Text (style-controlled, overall)
- LMArena Text (style-controlled, coding)
- LMArena Text (style-controlled, math)
- LMArena Text (style-controlled, hard prompts)
- LMArena Text (style-controlled, longer query)
- LMArena Text factuality
- Lab: xAI
Is Grok 4.20 Multi Agent Beta SOTA?
Best current rank: #45 in General LLM, as of Nov 22, 2026.
What is Grok 4.20 Multi Agent Beta best at?
As of Nov 22, 2026, Grok 4.20 Multi Agent Beta is ranked #45 in General LLM (since Nov 22, 2026; sources LMArena Text (style-controlled, overall)).
How does Grok 4.20 Multi Agent Beta rank in Coding?
As of Nov 22, 2026, Grok 4.20 Multi Agent Beta is short of the evidence for a rank in Coding (since Nov 22, 2026; sources LMArena Text (style-controlled, coding); methodology v1.0).