Grok 4.20
Apr 2026
Grok 4.20Compare inon
Benchmarks of Grok 4.2026
BenchmarkByScoreRank
Overall1
Knowledge5
Reasoning5
Math2
Science2
Coding1
Multimodal1
Health & law4
Documents1
Legacy · saturated or no longer reported4
No benchmark matches
Rankingin thinking mode?
Retired models are left out of the current rankings.
Alternatives?
ModelScoreCostPer taskWhat changes
CheaperMiMo v2.6 ProthinkingOpen+81%-65%$0.13Context: 2M → 1M+4
BetterGPT-6 Lunamedium+17%-87%$0.017Context: 2M → 1.05M+4
CheaperDeepSeek V4.1 Flash 1017maxOpen+76%-66%$0.26Context: 2M → 1M+5
CheaperLing 3.1 Flash 1019+71%-71%$1.49Context: 2M → 1M+1
CheaperStep 5 PreviewthinkingOpen+70%-9%$1.03Context: 2M → 1M+3ModelScoreCostPer taskWhat changes
MiMo v2.6 ProthinkingOpen+81%-65%$0.13Context: 2M → 1M+4DeepSeek V4.1 Flash 1017maxOpen+76%-66%$0.26Context: 2M → 1M+5Ling 3.1 Flash 1019+71%-71%$1.49Context: 2M → 1M+1Step 5 PreviewthinkingOpen+70%-9%$1.03Context: 2M → 1M+3
Claude Haiku 5.5max+69%-87%$0.21Context: 2M → 1M+6ModelScoreCostPer taskWhat changes
GPT-6 Lunamedium+17%-87%$0.017Context: 2M → 1.05M+4Claude Haiku 5.5low+15%-87%$0.024Context: 2M → 1M+6GPT-5.6 Lunahigh+25%-71%$0.044Context: 2M → 1.05MGPT-6.1 Terralow+41%+28%$0.055Context: 2M → 1.05MMiMo v2.6 FlashthinkingOpen+48%-89%$0.062Context: 2M → 1M+4ModelScoreCostPer taskWhat changes
MiMo v2.6 ProthinkingOpen+81%-65%$0.13Context: 2M → 1M+4DeepSeek V4.1 Flash 1017maxOpen+76%-66%$0.26Context: 2M → 1M+5
GLM 5.3maxOpen+75%+38%$2.01Context: 2M → 1M+5Step 5 PreviewthinkingOpen+70%-9%$1.03Context: 2M → 1M+3
Kimi K3maxOpen+70%+284%$2.00Context: 2M → 1M+4ModelScoreCostPer taskWhat changes
Grok 4.6medium+67%—$1.14Context: 2M → 500KGrok 4.7low+65%—$1.03Context: 2M → 500K+5Grok 4.5high+51%—$0.76Context: 2M → 500KGrok Build 0.1thinking+6%—$1 / $2Context: 2M → 256KGrok 4.3mediumsame—$1.25 / $2.50Context: 2M → 1MGrok 4.20 Multi-Agentn/a—$1.25 / $2.50Grok 4.20 Non-Reasoningn/a—$1.25 / $2.50Context: not verifiedGrok 4.20 Reasoningn/a—$1.25 / $2.50Context: not verifiedAll xAI models →History
8 versionsBenchmarks
all categoriesChat & Knowledge
Vals LegalBench77.7
Vals MedCode32.2
Vals MedScribe63.4
HealthBench Professional length-adjustedlab36.1
GPQA Diamond91.1
Coding
Agents & Tool Use
Writing & Language
Vision & Documents
FAQ
How much does Grok 4.20 cost?›
$1.25 per 1M input tokens and $2.50 per 1M output tokens; cached input $0.20 per 1M.
Is Grok 4.20 free to use?›
There is no free API; the cheapest paid price is $1.25 per 1M input tokens.
How can I use Grok 4.20?›
Through the API of xAI.
What is the context window of Grok 4.20?›
2M tokens, with up to 1.8M output tokens.
When was Grok 4.20 released? Is there a newer version?›
Released 2026-04-07. It has been superseded by Grok 4.3.
Is Grok 4.20 open source?›
No, Grok 4.20 is a closed model available through an API. The closest open-weights option here is MiMo v2.6 Pro.
Can Grok 4.20 read images?›
It accepts text and images, PDF files as input.
What is Grok 4.20?›
Grok 4.20 is a closed language model from xAI, released Apr 2026, the successor to Grok 4.20 0309.
What are the best alternatives to Grok 4.20?›
MiMo v2.6 Pro (cheaper), GPT-6 Luna (better).