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

# Grok 4

| Field | Value |
| --- | --- |
| Organization | xAI |
| License | Proprietary |
| Version | Latest |
| Released | 2025-07-09 |
| Context window | 256K |
| Input cost per million tokens | $3 |
| Output cost per million tokens | $15 |
| Cached input cost per million tokens | $0.75 |
| Model ID | grok-4-0709 |
| Last updated | 2026-05-03T23:55:01.103Z |

## Benchmarks

| Benchmark | Category | Value | Description | Source |
| --- | --- | --- | --- | --- |
| RankedAGI Coding | coding | 58.7% | RankedAGI Coding Score |  |
| RankedAGI Agentic | Agents | 51.2% | RankedAGI Agentic Score |  |
| Code Arena | coding | 1149 | Code Arena Elo Score | https://arena.ai/leaderboard/code |
| LiveBench Coding 25.5 | coding | 71.3% | LiveBench Coding Score 2025-05-30 |  |
| Aider Polyglot | coding | 79.6% | Aider Polyglot Code Completion Benchmark |  |
| RankedAGI Reasoning | reasoning | 71.0% | RankedAGI Reasoning Score |  |
| Humanity's Last Exam | reasoning | 38.6% | Multidisciplinary Reasoning (no tools) |  |
| GPQA Diamond | reasoning | 87.5% | Generalized Prefix Question Answering Score (Reasoning) PhD Level Reasoning |  |
| LiveBench Reasoning 25.5 | reasoning | 97.8% | LiveBench Reasoning Score 2025-05-30 |  |
| Text Arena | general | 1410 | ChatArena (LMSYS) ELO Score | https://arena.ai/leaderboard/text |
| AIME 2025 | math | 98.8% | AIME 2025 Competition Math |  |
| LiveBench Math Score | math | 88.8% | LiveBench Math Score 25-05 |  |
| LiveBench IF 25.5 | instruction-following | 78.1% | LiveBench Instruction Following Score 2025-05-30 |  |
| LiveBench Average 25.5 | general | 72.1% | LiveBench Average Score 2025-05-30 |  |
| LiveBench Agentic Coding 25.5 | coding | 23.3% | LiveBench Agentic Coding Score 2025-05-30 | https://livebench.ai/ |
| RankedAGI Math | math | 79.5% | RankedAGI Math Score |  |
| RankedAGI Overall | general | 58.6% | Overall RankedAGI score |  |
| GDPval-AA Elo | Agents | 976 | Office Tasks (Artificial Analysis) |  |
| SvelteBench old | coding | 87.8% | SvelteBench - Benchmark for Svelte (Old v1) | https://khromov.github.io/svelte-bench/v1/v1-benchmark-results-merged.html |
| Code DesignArena | Design | 1157 |  | https://www.designarena.ai/leaderboard/code |
| Toolathlon | Agents | 27.5% | Benchmark to assess language agents' general tool use in realistic environments. | https://toolathlon.xyz/introduction |

## Model Links

| Title | URL |
| --- | --- |
| Release | https://x.ai/news/grok-4 |