---
title: "Grok 4.2 Benchmarks - RankedAGI"
description: "Detailed benchmark and metadata record for Grok 4.2."
source: "https://rankedagi.com/models/grok-4-20"
---

# Grok 4.2

| Field | Value |
| --- | --- |
| Organization | xAI |
| License | Proprietary |
| Type | Thinking |
| Version | Latest |
| Released | 2026-03-31 |
| Context window | 2M |
| Knowledge cutoff | 2025-09-01 |
| Input cost per million tokens | $2 |
| Output cost per million tokens | $6 |
| Cached input cost per million tokens | $0.2 |
| Model ID | x-ai/grok-4.20 |
| Last updated | 2026-05-03T23:35:38.867Z |

## Benchmarks

| Benchmark | Category | Value | Description | Source |
| --- | --- | --- | --- | --- |
| RankedAGI Coding | coding | 70.0% | RankedAGI Coding Score |  |
| RankedAGI Agentic | Agents | 60.1% | RankedAGI Agentic Score |  |
| Code Arena | coding | 1402 | Code Arena Elo Score | https://arena.ai/leaderboard/code |
| Livebench Coding 26.1 | coding | 66.1% | Livebench Coding 26.01.08 | https://livebench.ai/#/?Coding=a&sort=Coding+Average&variants=true&highunseenbias=true |
| LiveBench Agentic Coding 26.1 | coding | 43.3% |  | https://livebench.ai/#/?Agentic+Coding=a&sort=Agentic+Coding+Average&variants=true&highunseenbias=true |
| SvelteBench | coding | 88.9% | SvelteBench - Benchmark for Svelte | https://khromov.github.io/svelte-bench/benchmark-results-merged.html |
| RankedAGI Reasoning | reasoning | 69.6% | RankedAGI Reasoning Score |  |
| Humanity's Last Exam | reasoning | 32.0% | Multidisciplinary Reasoning (no tools) |  |
| GPQA Diamond | reasoning | 91.0% | Generalized Prefix Question Answering Score (Reasoning) PhD Level Reasoning |  |
| Text Arena | general | 1480 | ChatArena (LMSYS) ELO Score | https://arena.ai/leaderboard/text |
| Vending Bench 2 | Agents | $4,662.85 | Benchmark for measuring AI model performance on running a business over long time horizons. Models are tasked with running a simulated vending machine business over a year and scored on their bank account balance at the end. | https://andonlabs.com/evals/vending-bench-2 |
| NYT Connections Extended | reasoning | 90.3% | NYT Connections Extended Version | https://github.com/lechmazur/nyt-connections/ |
| Instruction Following Evaluation | instruction-following | 81.0% | Instruction Following Evaluation |  |
| MMMU-Pro | imaging | 75.0% | Multimodal Understanding |  |
| RankedAGI Math | math | 72.3% | RankedAGI Math Score |  |
| RankedAGI Overall | general | 62.3% | Overall RankedAGI score |  |
| ARC AGI 2 | reasoning | 53.3% | Abstract Reasoning Puzzles (Public) |  |
| LiveCodeBench Pro | coding | 74.2% | Competitive Coding |  |
| 𝜏²-Bench Telecom | Agents | 96.5% | Agentic Tool Use |  |
| HealthBench Hard | Health | 20.3% | Open-ended Health Queries |  |
| MedXpertQA Text | Health | 50.2% | Medical Multiple Choice |  |
| MedXpertQA (MM) | Health | 65.8% | Medical Multiple Choice |  |
| DeepSearch QA | Agents | 62.8% | Agentic Search |  |
| GDPval-AA Elo | Agents | 1180 | Office Tasks (Artificial Analysis) |  |
| CharXiv Reasoning | Multimodal | 60.9% | Figure Understanding |  |
| Code DesignArena | Design | 1274 |  | https://www.designarena.ai/leaderboard/code |

## Model Links

| Title | URL |
| --- | --- |
| OpenRouter | https://openrouter.ai/x-ai/grok-4.20 |
| AA | https://artificialanalysis.ai/models/grok-4-20 |