---
title: "GPT-5 Thinking Benchmarks - RankedAGI"
description: "Detailed benchmark and metadata record for GPT-5 Thinking."
source: "https://rankedagi.com/models/gpt-5-thinking"
---

# GPT-5 Thinking

| Field | Value |
| --- | --- |
| Organization | OpenAI |
| License | Proprietary |
| Type | Thinking |
| Version | Latest |
| Released | 2025-08-07 |
| Last updated | 2026-05-04T00:11:22.887Z |

## Benchmarks

| Benchmark | Category | Value | Description | Source |
| --- | --- | --- | --- | --- |
| RankedAGI Coding | coding | 65.2% | RankedAGI Coding Score |  |
| SWEBench Verified | coding | 74.9% | Agentic Coding | https://www.swebench.com/index.html |
| RankedAGI Agentic | Agents | 58.2% | RankedAGI Agentic Score |  |
| BrowseComp | Agents | 54.9% | A benchmark for browsing agents | https://openai.com/index/browsecomp/ |
| Aider Polyglot | coding | 88.0% | Aider Polyglot Code Completion Benchmark |  |
| RankedAGI Reasoning | reasoning | 63.8% | RankedAGI Reasoning Score |  |
| Humanity's Last Exam | reasoning | 24.8% | Multidisciplinary Reasoning (no tools) |  |
| Humanity's Last Exam w/ Tools | reasoning | 35.2% | Multidisciplinary Reasoning (with tools) |  |
| GPQA Diamond | reasoning | 87.3% | Generalized Prefix Question Answering Score (Reasoning) PhD Level Reasoning |  |
| Text Arena | general | 1434 | ChatArena (LMSYS) ELO Score | https://arena.ai/leaderboard/text |
| AIME 2025 | math | 99.6% | AIME 2025 Competition Math |  |
| MMMU | imaging | 84.2% | Multimodal Understanding College-level visual problem-solving |  |
| MMMU-Pro | imaging | 78.4% | Multimodal Understanding |  |
| RankedAGI Math | math | 76.8% | RankedAGI Math Score |  |
| RankedAGI Overall | general | 59.8% | Overall RankedAGI score |  |
| 𝜏²-Bench Telecom | Agents | 96.7% | Agentic Tool Use |  |
| 𝜏²-Bench Retail | Agents | 81.0% | Agentic Tool Use |  |
| 𝜏²-Bench Airline | Agents | 62.6% | Agentic Tool Use |  |
| HealthBench Hard | Health | 46.2% | Open-ended Health Queries |  |
| GDPval-AA Elo | Agents | 1301 | Office Tasks (Artificial Analysis) |  |
| SvelteBench old | coding | 77.8% | SvelteBench - Benchmark for Svelte (Old v1) | https://khromov.github.io/svelte-bench/v1/v1-benchmark-results-merged.html |
| Code DesignArena | Design | 1219 |  | https://www.designarena.ai/leaderboard/code |