---
title: "GPT 5.4 nano Benchmarks - RankedAGI"
description: "Detailed benchmark and metadata record for GPT 5.4 nano."
source: "https://rankedagi.com/models/gpt-5-4-nano"
---

# GPT 5.4 nano

| Field | Value |
| --- | --- |
| Organization | OpenAI |
| License | Proprietary |
| Type | Thinking |
| Version | Latest |
| Released | 2026-03-17 |
| Context window | 400K |
| Knowledge cutoff | 2025-08-31 |
| Input cost per million tokens | $0.2 |
| Output cost per million tokens | $1.25 |
| Cached input cost per million tokens | $0.02 |
| Last updated | 2026-05-04T00:11:22.887Z |

## Benchmarks

| Benchmark | Category | Value | Description | Source |
| --- | --- | --- | --- | --- |
| RankedAGI Coding | coding | 55.1% | RankedAGI Coding Score |  |
| SWEBench Pro | coding | 52.4% | Diverse Agentic Coding |  |
| Terminal-Bench 2.0 | coding | 46.3% | Agentic Terminal Coding | https://www.tbench.ai/leaderboard/terminal-bench/2.0 |
| RankedAGI Agentic | Agents | 48.6% | RankedAGI Agentic Score |  |
| Livebench Coding 26.1 | coding | 68.4% | Livebench Coding 26.01.08 | https://livebench.ai/#/?Coding=a&sort=Coding+Average&variants=true&highunseenbias=true |
| LiveBench Agentic Coding 26.1 | coding | 49.1% |  | https://livebench.ai/#/?Agentic+Coding=a&sort=Agentic+Coding+Average&variants=true&highunseenbias=true |
| OSWorld-Verified | Agents | 39.0% |  |  |
| SvelteBench | coding | 63.3% | SvelteBench - Benchmark for Svelte | https://khromov.github.io/svelte-bench/benchmark-results-merged.html |
| RankedAGI Reasoning | reasoning | 58.9% | RankedAGI Reasoning Score |  |
| Humanity's Last Exam | reasoning | 24.3% | Multidisciplinary Reasoning (no tools) |  |
| Humanity's Last Exam w/ Tools | reasoning | 24.3% | Multidisciplinary Reasoning (with tools) |  |
| GPQA Diamond | reasoning | 82.8% | Generalized Prefix Question Answering Score (Reasoning) PhD Level Reasoning |  |
| Text Arena | general | 1406 | ChatArena (LMSYS) ELO Score | https://arena.ai/leaderboard/text |
| MMMU-Pro | imaging | 66.1% | Multimodal Understanding |  |
| MMMU Pro w/Tools | imaging | 69.5% |  |  |
| RankedAGI Math | math | 68.4% | RankedAGI Math Score |  |
| RankedAGI Overall | general | 54.1% | Overall RankedAGI score |  |
| 𝜏²-Bench Telecom | Agents | 92.5% | Agentic Tool Use |  |
| GDPval-AA Elo | Agents | 1177 | Office Tasks (Artificial Analysis) |  |
| MCP Atlas | Agents | 56.1% | Scaled Tool Use |  |
| Toolathlon | Agents | 35.5% | 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-gpt-5-4-mini-and-nano/ |