Sign in

Is Grok 4.20 Beta SOTA in Reasoning?#47 in ReasoningRanked #47 in Reasoning.

How it scores here

Grok 4.20 Beta in Reasoning

Primary benchmarks

  • LMArena Text (style-controlled, hard prompts): 1489 (CI 1484–1493) on Nov 19, 2026 (#56 of 263).

On the category's weighted score it is 28.2 points behind #1 Gemini 4 Carbon and 0.6 behind the next model up, Claude Sonnet 5.

Nearby on the board

#ModelCategory score
44GPT-5.5 Instant73.5
45GPT-5.6 Terra72.9
46Claude Sonnet 572.4
47Grok 4.20 Beta71.8
48GLM 5.171.2
49Grok 4.570.6
50Grok 4.20 Beta 170.0
Standings

Reasoning

#ModelState
1Gemini 4 CarbonCo-SOTA
1Gemini 4 ArgonCo-SOTA
1Gemini 4 NeonCo-SOTA
2Muse WonderNear-SOTA
3Claude Opus 4.6Near-SOTA
4Claude Opus 5.5Near-SOTA
5Claude Fable 5Near-SOTA
6Claude Opus 4.7Was SOTA
7Claude Fable 5.1Was SOTA
8Muse Spark 1.3#8 in this category
9Gemini 3.8 Flash#9 in this category
10Claude Fable 5.2#10 in this category

Category page →