---
title: "Grok 3 Benchmarks - RankedAGI"
description: "Detailed benchmark and metadata record for Grok 3."
source: "https://rankedagi.com/models/grok-3"
---

# Grok 3

| Field | Value |
| --- | --- |
| Organization | xAI |
| License | Proprietary |
| Version | Latest |
| Released | 2025-02-17 |
| Context window | 130K |
| Knowledge cutoff | 2024-11-17 |
| Input cost per million tokens | $3 |
| Output cost per million tokens | $15 |
| Model ID | grok-3 |
| Last updated | 2026-05-03T23:55:01.103Z |

## Benchmarks

| Benchmark | Category | Value | Description | Source |
| --- | --- | --- | --- | --- |
| RankedAGI Coding | coding | 47.4% | RankedAGI Coding Score |  |
| RankedAGI Agentic | Agents | 39.6% | RankedAGI Agentic Score |  |
| ChatArena (LMSYS) | coding | 1335 | ChatArena (LMSYS) Coding ELO Score with Style Control |  |
| Aider Polyglot | coding | 53.3% | Aider Polyglot Code Completion Benchmark |  |
| RankedAGI Reasoning | reasoning | 47.4% | RankedAGI Reasoning Score |  |
| GPQA Diamond | reasoning | 75.4% | Generalized Prefix Question Answering Score (Reasoning) PhD Level Reasoning |  |
| Text Arena | general | 1399 | ChatArena (LMSYS) ELO Score | https://arena.ai/leaderboard/text |
| AIME 2024 | math | 52.2% | AIME 2024 Competition Math |  |
| MMLU Pro | knowledge | 79.9% | Graduate-level visual problem-solving |  |
| MMMU | imaging | 73.2% | Multimodal Understanding College-level visual problem-solving |  |
| Hughes Hallucination Evaluation | safety | 2.1% | 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 |
| LiveBench Coding 25.4 | coding | 37.3% | LiveBench Coding Score 2025-04 | https://livebench.ai/ |
| RankedAGI Math | math | 58.1% | RankedAGI Math Score |  |
| RankedAGI Overall | general | 47.5% | Overall RankedAGI score |  |
| GDPval-AA Elo | Agents | 666 | Office Tasks (Artificial Analysis) |  |
| SvelteBench old | coding | 83.3% | SvelteBench - Benchmark for Svelte (Old v1) | https://khromov.github.io/svelte-bench/v1/v1-benchmark-results-merged.html |
| Code DesignArena | Design | 1103 |  | https://www.designarena.ai/leaderboard/code |

## Model Links

| Title | URL |
| --- | --- |
| Release | https://x.ai/blog/grok-3 |