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

# GPT 4o

| Field | Value |
| --- | --- |
| Organization | OpenAI |
| License | Proprietary |
| Version | Old |
| Released | 2024-11-20 |
| Context window | 128K |
| Knowledge cutoff | 2023-11-01 |
| Input cost per million tokens | $2.5 |
| Output cost per million tokens | $10 |
| Model ID | gpt-4o-2024-11-20 |
| Last updated | 2026-05-04T00:13:11.660Z |

## Benchmarks

| Benchmark | Category | Value | Description | Source |
| --- | --- | --- | --- | --- |
| RankedAGI Coding | coding | 31.1% | RankedAGI Coding Score |  |
| SWEBench Verified | coding | 31.0% | Agentic Coding | https://www.swebench.com/index.html |
| RankedAGI Agentic | Agents | 25.9% | RankedAGI Agentic Score |  |
| ChatArena (LMSYS) | coding | 1306 | ChatArena (LMSYS) Coding ELO Score with Style Control |  |
| Aider Polyglot | coding | 18.2% | Aider Polyglot Code Completion Benchmark |  |
| LiveBench Coding Score (old) | coding | 46.1% | LiveBench Coding Score old version |  |
| RankedAGI Reasoning | reasoning | 31.9% | RankedAGI Reasoning Score |  |
| GPQA Diamond | reasoning | 39.0% | Generalized Prefix Question Answering Score (Reasoning) PhD Level Reasoning |  |
| Text Arena | general | 1361 | ChatArena (LMSYS) ELO Score | https://arena.ai/leaderboard/text |
| AIME 2025 | math | 13.0% | AIME 2025 Competition Math |  |
| HumanEval | coding | 90.0% | HumanEval coding benchmark |  |
| NYT Connections Extended | reasoning | 18.7% | NYT Connections Extended Version | https://github.com/lechmazur/nyt-connections/ |
| MMLU Pro | knowledge | 74.7% | Graduate-level visual problem-solving |  |
| MMLU | knowledge | 86.0% | Image Reasoning |  |
| Hughes Hallucination Evaluation | safety | 1.5% | 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 |
| AidanBench | general | 1269 | AidanBench Score |  |
| LiveBench Average | general | 53.2% | LiveBench Average Score old version |  |
| Instruction Following Evaluation | instruction-following | 84.6% | Instruction Following Evaluation |  |
| LiveBench Coding 25.4 | coding | 35.2% | LiveBench Coding Score 2025-04 | https://livebench.ai/ |
| LiveBench Data Analysis | general | 47.2% | LiveBench Data Analysis Score | https://livebench.ai/ |
| LiveBench Language | general | 47.4% | LiveBench Language Score | https://livebench.ai/ |
| Artificial Analysis Quality Index | general | 71 | Artificial Analysis Quality Index (third-party composite, deprecated) |  |
| RankedAGI Math | math | 36.3% | RankedAGI Math Score |  |
| RankedAGI Overall | general | 36.5% | Overall RankedAGI score |  |