---
title: "Grok 4.1 Fast Benchmarks - RankedAGI"
description: "Detailed benchmark and metadata record for Grok 4.1 Fast."
source: "https://rankedagi.com/models/grok-4-1-fast"
---

# Grok 4.1 Fast

| Field | Value |
| --- | --- |
| Organization | xAI |
| License | Proprietary |
| Type | Non-thinking |
| Version | Latest |
| Released | 2025-11-19 |
| Context window | 2M |
| Input cost per million tokens | $0.2 |
| Output cost per million tokens | $0.5 |
| Cached input cost per million tokens | $0.05 |
| Last updated | 2026-06-17T19:00:49.160Z |

## Benchmarks

| Benchmark | Category | Value | Description | Source |
| --- | --- | --- | --- | --- |
| RankedAGI Coding | coding | 39.9% | RankedAGI Coding Score |  |
| RankedAGI Agentic | Agents | 32.4% | RankedAGI Agentic Score |  |
| SvelteBench | coding | 80.0% | SvelteBench - Benchmark for Svelte | https://khromov.github.io/svelte-bench/benchmark-results-merged.html |
| LiveCodeBench v6 | coding | 40.0% | LiveCodeBench v6 - Evaluation of Large Language Models for Code |  |
| RankedAGI Reasoning | reasoning | 36.5% | RankedAGI Reasoning Score |  |
| Humanity's Last Exam | reasoning | 5.0% | Multidisciplinary Reasoning (no tools) |  |
| GPQA Diamond | reasoning | 64.0% | Generalized Prefix Question Answering Score (Reasoning) PhD Level Reasoning |  |
| AIME 2025 | math | 34.0% | AIME 2025 Competition Math |  |
| Instruction Following Evaluation | instruction-following | 37.0% | Instruction Following Evaluation |  |
| MMMU-Pro | imaging | 48.0% | Multimodal Understanding |  |
| RankedAGI Math | math | 48.8% | RankedAGI Math Score |  |
| RankedAGI Overall | general | 41.1% | Overall RankedAGI score |  |
| 𝜏²-Bench Telecom | Agents | 64.0% | Agentic Tool Use |  |
| Code DesignArena | Design | 1143 |  | https://www.designarena.ai/leaderboard/code |

## Model Links

| Title | URL |
| --- | --- |
| Release | https://x.ai/news/grok-4-1-fast |