---
title: "GPT 4.5 Benchmarks - RankedAGI"
description: "Detailed benchmark and metadata record for GPT 4.5."
source: "https://rankedagi.com/models/gpt-4.5-preview"
---

# GPT 4.5

| Field | Value |
| --- | --- |
| Organization | OpenAI |
| License | Proprietary |
| Version | Preview |
| Released | 2025-02-27 |
| Context window | 128K |
| Input cost per million tokens | $75 |
| Output cost per million tokens | $150 |
| Cached input cost per million tokens | $37.5 |
| Model ID | gpt-4.5-preview |
| Last updated | 2025-06-06 12:54:56.587541+00 |

## Benchmarks

| Benchmark | Category | Value | Description | Source |
| --- | --- | --- | --- | --- |
| RankedAGI Coding | coding | 48.8% | RankedAGI Coding Score |  |
| SWEBench Verified | coding | 38.0% | Agentic Coding | https://www.swebench.com/index.html |
| RankedAGI Agentic | Agents | 42.5% | RankedAGI Agentic Score |  |
| ChatArena (LMSYS) | coding | 1362 | ChatArena (LMSYS) Coding ELO Score with Style Control |  |
| Aider Polyglot | coding | 45.0% | Aider Polyglot Code Completion Benchmark |  |
| LiveBench Coding Score (old) | coding | 75.2% | LiveBench Coding Score old version |  |
| RankedAGI Reasoning | reasoning | 47.0% | RankedAGI Reasoning Score |  |
| GPQA Diamond | reasoning | 71.4% | Generalized Prefix Question Answering Score (Reasoning) PhD Level Reasoning |  |
| Text Arena | general | 1425 | ChatArena (LMSYS) ELO Score | https://arena.ai/leaderboard/text |
| AIME 2024 | math | 36.7% | AIME 2024 Competition Math |  |
| NYT Connections Extended | reasoning | 34.2% | NYT Connections Extended Version | https://github.com/lechmazur/nyt-connections/ |
| MMMU | imaging | 74.4% | Multimodal Understanding College-level visual problem-solving |  |
| Hughes Hallucination Evaluation | safety | 1.2% | 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 |
| LiveBench Average | general | 69.0% | LiveBench Average Score old version |  |
| LiveBench Coding 25.4 | coding | 76.1% | LiveBench Coding Score 2025-04 | https://livebench.ai/ |
| LiveBench Data Analysis | general | 64.3% | LiveBench Data Analysis Score | https://livebench.ai/ |
| LiveBench Language | general | 61.5% | LiveBench Language Score | https://livebench.ai/ |
| RankedAGI Math | math | 54.9% | RankedAGI Math Score |  |
| RankedAGI Overall | general | 48.2% | Overall RankedAGI score |  |

## Model Links

| Title | URL |
| --- | --- |
| Release | https://openai.com/index/introducing-gpt-4-5/ |