---
title: "GPT 4o mini Benchmarks - RankedAGI"
description: "Detailed benchmark and metadata record for GPT 4o mini."
source: "https://rankedagi.com/models/gpt-4o-mini"
---

# GPT 4o mini

| Field | Value |
| --- | --- |
| Organization | OpenAI |
| License | Proprietary |
| Version | Latest |
| Released | 2024-07-18 |
| Context window | 128K |
| Knowledge cutoff | 2023-10-01 |
| Input cost per million tokens | $0.15 |
| Output cost per million tokens | $0.6 |
| Model ID | gpt-4o-mini |
| Last updated | 2025-06-06 05:45:23.928607+00 |

## Benchmarks

| Benchmark | Category | Value | Description | Source |
| --- | --- | --- | --- | --- |
| RankedAGI Coding | coding | 28.7% | RankedAGI Coding Score |  |
| RankedAGI Agentic | Agents | 25.9% | RankedAGI Agentic Score |  |
| LiveCodeBench v6 | coding | 27.5% | LiveCodeBench v6 - Evaluation of Large Language Models for Code |  |
| ChatArena (LMSYS) | coding | 1245 | ChatArena (LMSYS) Coding ELO Score with Style Control |  |
| Aider Polyglot | coding | 3.6% | Aider Polyglot Code Completion Benchmark |  |
| LiveBench Coding Score (old) | coding | 43.1% | LiveBench Coding Score old version |  |
| RankedAGI Reasoning | reasoning | 32.1% | RankedAGI Reasoning Score |  |
| GPQA Diamond | reasoning | 43.0% | Generalized Prefix Question Answering Score (Reasoning) PhD Level Reasoning |  |
| Text Arena | general | 1272 | ChatArena (LMSYS) ELO Score | https://arena.ai/leaderboard/text |
| HumanEval | coding | 87.2% | HumanEval coding benchmark |  |
| HumanEval+ | coding | 83.5% | HumanEval+ benchmark |  |
| NYT Connections Extended | reasoning | 9.9% | NYT Connections Extended Version | https://github.com/lechmazur/nyt-connections/ |
| MMLU Pro | knowledge | 63.1% | Graduate-level visual problem-solving |  |
| MMLU | knowledge | 82.0% | Image Reasoning |  |
| Hughes Hallucination Evaluation | safety | 1.7% | 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 Average | general | 43.3% | LiveBench Average Score old version |  |
| LiveBench Coding 25.4 | coding | 25.5% | LiveBench Coding Score 2025-04 | https://livebench.ai/ |
| LiveBench Data Analysis | general | 44.5% | LiveBench Data Analysis Score | https://livebench.ai/ |
| LiveBench Language | general | 28.6% | LiveBench Language Score | https://livebench.ai/ |
| Artificial Analysis Quality Index | general | 71 | Artificial Analysis Quality Index (third-party composite, deprecated) |  |
| RankedAGI Math | math | 41.0% | RankedAGI Math Score |  |
| RankedAGI Overall | general | 36.2% | Overall RankedAGI score |  |