---
title: "o4 mini Benchmarks - RankedAGI"
description: "Detailed benchmark and metadata record for o4 mini."
source: "https://rankedagi.com/models/o4-mini"
---

# o4 mini

| Field | Value |
| --- | --- |
| Organization | OpenAI |
| License | Proprietary |
| Version | Latest |
| Released | 2025-04-16 |
| Context window | 200K |
| Knowledge cutoff | 2024-06-01 |
| Input cost per million tokens | $1.1 |
| Output cost per million tokens | $4.4 |
| Cached input cost per million tokens | $0.28 |
| Model ID | o4-mini-2025-04-16 |
| Last updated | 2026-05-04T03:43:08.354Z |

## Benchmarks

| Benchmark | Category | Value | Description | Source |
| --- | --- | --- | --- | --- |
| RankedAGI Coding | coding | 53.2% | RankedAGI Coding Score |  |
| SWEBench Verified | coding | 68.1% | Agentic Coding | https://www.swebench.com/index.html |
| RankedAGI Agentic | Agents | 41.8% | RankedAGI Agentic Score |  |
| LiveBench Coding 25.5 | coding | 74.2% | LiveBench Coding Score 2025-05-30 |  |
| ChatArena (LMSYS) | coding | 1334 | ChatArena (LMSYS) Coding ELO Score with Style Control |  |
| CyberGym | safety | 2.5% |  |  |
| Codeforces ELO Score | coding | 2719 | Codeforces ELO Score |  |
| RankedAGI Reasoning | reasoning | 53.2% | RankedAGI Reasoning Score |  |
| Humanity's Last Exam | reasoning | 18.1% | Multidisciplinary Reasoning (no tools) |  |
| GPQA Diamond | reasoning | 81.4% | Generalized Prefix Question Answering Score (Reasoning) PhD Level Reasoning |  |
| LiveBench Reasoning 25.5 | reasoning | 78.5% | LiveBench Reasoning Score 2025-05-30 |  |
| Text Arena | general | 1390 | ChatArena (LMSYS) ELO Score | https://arena.ai/leaderboard/text |
| AIME 2025 | math | 84.0% | AIME 2025 Competition Math |  |
| LiveBench Math Score | math | 81.0% | LiveBench Math Score 25-05 |  |
| MMMU | imaging | 81.6% | Multimodal Understanding College-level visual problem-solving |  |
| 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 |
| LiveBench IF 25.5 | instruction-following | 81.8% | LiveBench Instruction Following Score 2025-05-30 |  |
| LiveBench Average 25.5 | general | 67.4% | LiveBench Average Score 2025-05-30 |  |
| LiveBench Coding 25.4 | coding | 61.8% | LiveBench Coding Score 2025-04 | https://livebench.ai/ |
| LiveBench Agentic Coding 25.5 | coding | 21.7% | LiveBench Agentic Coding Score 2025-05-30 | https://livebench.ai/ |
| RankedAGI Math | math | 61.4% | RankedAGI Math Score |  |
| RankedAGI Overall | general | 50.6% | Overall RankedAGI score |  |
| SvelteBench old | coding | 13.3% | SvelteBench - Benchmark for Svelte (Old v1) | https://khromov.github.io/svelte-bench/v1/v1-benchmark-results-merged.html |
| Code DesignArena | Design | 1026 |  | https://www.designarena.ai/leaderboard/code |
| Toolathlon | Agents | 14.8% | Benchmark to assess language agents' general tool use in realistic environments. | https://toolathlon.xyz/introduction |

## Model Links

| Title | URL |
| --- | --- |
| Release | https://openai.com/index/introducing-o3-and-o4-mini/ |