---
title: "GPT 4.1 mini Benchmarks - RankedAGI"
description: "Detailed benchmark and metadata record for GPT 4.1 mini."
source: "https://rankedagi.com/models/gpt-4.1-mini"
---

# GPT 4.1 mini

| Field | Value |
| --- | --- |
| Organization | OpenAI |
| License | Proprietary |
| Version | Latest |
| Released | 2025-04-14 |
| Context window | 1M |
| Knowledge cutoff | 2024-06-01 |
| Input cost per million tokens | $0.4 |
| Output cost per million tokens | $1.6 |
| Cached input cost per million tokens | $0.1 |
| Model ID | gpt-4.1-mini-2025-04-14 |
| Last updated | 2026-05-04T00:13:11.660Z |

## Benchmarks

| Benchmark | Category | Value | Description | Source |
| --- | --- | --- | --- | --- |
| RankedAGI Coding | coding | 33.7% | RankedAGI Coding Score |  |
| SWEBench Verified | coding | 24.0% | Agentic Coding | https://www.swebench.com/index.html |
| RankedAGI Agentic | Agents | 26.2% | RankedAGI Agentic Score |  |
| Aider Polyglot | coding | 35.0% | Aider Polyglot Code Completion Benchmark |  |
| RankedAGI Reasoning | reasoning | 41.3% | RankedAGI Reasoning Score |  |
| GPQA Diamond | reasoning | 65.0% | Generalized Prefix Question Answering Score (Reasoning) PhD Level Reasoning |  |
| Text Arena | general | 1365 | ChatArena (LMSYS) ELO Score | https://arena.ai/leaderboard/text |
| AIME 2024 | math | 49.6% | AIME 2024 Competition Math |  |
| MMLU | knowledge | 87.5% | Image Reasoning |  |
| MMMU | imaging | 73.0% | Multimodal Understanding College-level visual problem-solving |  |
| Hughes Hallucination Evaluation | safety | 2.2% | 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 |
| Instruction Following Evaluation | instruction-following | 84.0% | Instruction Following Evaluation |  |
| LiveBench Coding 25.4 | coding | 47.6% | LiveBench Coding Score 2025-04 | https://livebench.ai/ |
| RankedAGI Math | math | 50.5% | RankedAGI Math Score |  |
| RankedAGI Overall | general | 40.0% | Overall RankedAGI score |  |
| GDPval-AA Elo | Agents | 619 | Office Tasks (Artificial Analysis) |  |
| SvelteBench old | coding | 1.1% | SvelteBench - Benchmark for Svelte (Old v1) | https://khromov.github.io/svelte-bench/v1/v1-benchmark-results-merged.html |
| Code DesignArena | Design | 1044 |  | https://www.designarena.ai/leaderboard/code |

## Model Links

| Title | URL |
| --- | --- |
| Release | https://openai.com/index/gpt-4-1/ |