---
title: "Grok 2 Benchmarks - RankedAGI"
description: "Detailed benchmark and metadata record for Grok 2."
source: "https://rankedagi.com/models/grok-2"
---

# Grok 2

| Field | Value |
| --- | --- |
| Organization | xAI |
| License | Proprietary |
| Version | Latest |
| Released | 2024-08-13 |
| Context window | 128K |
| Knowledge cutoff | 2024-08-01 |
| Input cost per million tokens | $5 |
| Output cost per million tokens | $15 |
| Last updated | 2026-05-03T23:55:01.103Z |

## Benchmarks

| Benchmark | Category | Value | Description | Source |
| --- | --- | --- | --- | --- |
| RankedAGI Coding | coding | 31.0% | RankedAGI Coding Score |  |
| RankedAGI Agentic | Agents | 25.9% | RankedAGI Agentic Score |  |
| ChatArena (LMSYS) | coding | 1253 | ChatArena (LMSYS) Coding ELO Score with Style Control |  |
| LiveBench Coding Score (old) | coding | 45.1% | LiveBench Coding Score old version |  |
| RankedAGI Reasoning | reasoning | 34.9% | RankedAGI Reasoning Score |  |
| Humanity's Last Exam | reasoning | 3.9% | Multidisciplinary Reasoning (no tools) |  |
| GPQA Diamond | reasoning | 56.0% | Generalized Prefix Question Answering Score (Reasoning) PhD Level Reasoning |  |
| Text Arena | general | 1335 | ChatArena (LMSYS) ELO Score | https://arena.ai/leaderboard/text |
| HumanEval | coding | 88.4% | HumanEval coding benchmark |  |
| HumanEval+ | coding | 80.5% | HumanEval+ benchmark |  |
| MMLU Pro | knowledge | 75.5% | Graduate-level visual problem-solving |  |
| MMLU | knowledge | 87.5% | Image Reasoning |  |
| Hughes Hallucination Evaluation | safety | 4.6% | Computed using Vectara's Hallucination Evaluation Model, also known as HHEM. This evaluates how often an LLM introduces hallucinations when summarizing a document. | https://github.com/vectara/hallucination-leaderboard |
| AidanBench | general | 826 | AidanBench Score |  |
| LiveBench Average | general | 54.4% | LiveBench Average Score old version |  |
| LiveBench Data Analysis | general | 50.3% | LiveBench Data Analysis Score | https://livebench.ai/ |
| LiveBench Language | general | 43.2% | LiveBench Language Score | https://livebench.ai/ |
| Artificial Analysis Quality Index | general | 70 | Artificial Analysis Quality Index (third-party composite, deprecated) |  |
| RankedAGI Math | math | 45.9% | RankedAGI Math Score |  |
| RankedAGI Overall | general | 37.7% | Overall RankedAGI score |  |