
Grok 4.20 Beta
Grok 4.20 Beta is a proprietary model from xAI. It ranks #51 of 351 on the LMArena text leaderboard with a rating of 1451.
LMArena text1451
Rank#51/351
95% interval1447–1455
Votes66.4K
- Developer
- xAI
- Released
- Oct 20, 2026
- Context window
- —
- Price in / out, per 1M tokens
- —
- Weights
- Proprietary
- Inputs
- —
- Reasoning
- —
- Tool use
- —
LMArena, by category
| Leaderboard | Rating | Rank | Votes |
|---|---|---|---|
| TextLMArena | 1451 | 51 / 351 | 66.4K |
| CodingLMArena | 1459 | 87 / 346 | 18.4K |
| MathLMArena | 1455 | 67 / 339 | 3.5K |
| Creative writingLMArena | 1432 | 59 / 349 | 11.4K |
| Instruction followingLMArena | 1421 | 86 / 351 | 22.6K |
| Hard promptsLMArena | 1451 | 72 / 351 | 43.5K |
| Multi-turnLMArena | 1456 | 54 / 349 | 12.1K |
| Long queriesLMArena | 1437 | 83 / 330 | 29.1K |
| ExpertLMArena | 1439 | 102 / 305 | 6.7K |
| Legal and governmentIndustries | 1454 | 62 / 325 | 5.3K |
| Medicine and healthcareIndustries | 1454 | 66 / 325 | 5K |
| Business and financeIndustries | 1432 | 76 / 344 | 13.4K |
| ChineseLanguages | 1481 | 74 / 328 | 4.2K |
| SpanishLanguages | 1442 | 79 / 249 | 2.1K |
| GermanLanguages | 1441 | 71 / 261 | 1K |
| FrenchLanguages | 1476 | 39 / 252 | 2.2K |
| JapaneseLanguages | 1415 | 60 / 236 | 706 |
| WebDevLMArena | 1376 | 109 / 124 | 15.5K |
| VisionLMArena | 1262 | 55 / 146 | 26.8K |
LMArena, CC BY 4.0, as of Oct 22, 2026. Where a model is rated at several effort levels, its best is shown.
Compare Grok 4.20 Beta
xAI
The lab behind Grok, trained on one of the largest compute clusters and integrated with X. Founded 2023, based in San Francisco Bay Area. x.ai
Questions
Who makes Grok 4.20 Beta?
Grok 4.20 Beta is made by xAI, founded 2023 and based in San Francisco Bay Area.
How does Grok 4.20 Beta rank?
#51 of 351 on LMArena’s text leaderboard, rated 1451 (95% interval 1447–1455) from 66,418 votes, as of Oct 22, 2026.
Is Grok 4.20 Beta open source?
No. Grok 4.20 Beta is proprietary and served through its provider’s API.
Gemini 4 Argon
Claude Opus 5.5
Muse Wonder
MiMo-V2.6-Pro
Qwen3.8-Max
Kimi K3
GLM-5.3
GPT-5.5
ERNIE 5.1
DeepSeek-V4.1-Flash-20260910
amazon-nova-experimental-chat
Dola Seed 2.0 Pro
NVIDIA-Nemotron-3-Ultra-550B-A55B
Gemma 4 31B
Step 5 Preview