---
title: "GPT 5.1 Benchmarks - RankedAGI"
description: "Detailed benchmark and metadata record for GPT 5.1."
source: "https://rankedagi.com/models/gpt-5-1"
---

# GPT 5.1

| Field | Value |
| --- | --- |
| Organization | OpenAI |
| License | Proprietary |
| Type | Thinking |
| Version | Latest |
| Released | 2025-11-12 |
| Input cost per million tokens | $1.25 |
| Output cost per million tokens | $10 |
| Cached input cost per million tokens | $0.13 |
| Last updated | 2026-05-04T02:07:02.436Z |

## Benchmarks

| Benchmark | Category | Value | Description | Source |
| --- | --- | --- | --- | --- |
| RankedAGI Coding | coding | 67.2% | RankedAGI Coding Score |  |
| SWEBench Pro | coding | 50.8% | Diverse Agentic Coding |  |
| SWEBench Verified | coding | 76.3% | Agentic Coding | https://www.swebench.com/index.html |
| RankedAGI Agentic | Agents | 56.0% | RankedAGI Agentic Score |  |
| Code Arena | coding | 1391 | Code Arena Elo Score | https://arena.ai/leaderboard/code |
| Livebench Coding 26.1 | coding | 72.5% | Livebench Coding 26.01.08 | https://livebench.ai/#/?Coding=a&sort=Coding+Average&variants=true&highunseenbias=true |
| LiveBench Agentic Coding 26.1 | coding | 53.3% |  | https://livebench.ai/#/?Agentic+Coding=a&sort=Agentic+Coding+Average&variants=true&highunseenbias=true |
| SvelteBench | coding | 80.0% | SvelteBench - Benchmark for Svelte | https://khromov.github.io/svelte-bench/benchmark-results-merged.html |
| RankedAGI Reasoning | reasoning | 58.3% | RankedAGI Reasoning Score |  |
| GPQA Diamond | reasoning | 88.1% | Generalized Prefix Question Answering Score (Reasoning) PhD Level Reasoning |  |
| Text Arena | general | 1455 | ChatArena (LMSYS) ELO Score | https://arena.ai/leaderboard/text |
| AIME 2025 | math | 94.0% | AIME 2025 Competition Math |  |
| Vending Bench 2 | Agents | $1,473.43 | Benchmark for measuring AI model performance on running a business over long time horizons. Models are tasked with running a simulated vending machine business over a year and scored on their bank account balance at the end. | https://andonlabs.com/evals/vending-bench-2 |
| RankedAGI Math | math | 75.6% | RankedAGI Math Score |  |
| RankedAGI Overall | general | 58.6% | Overall RankedAGI score |  |
| ARC AGI 2 | reasoning | 17.6% | Abstract Reasoning Puzzles (Public) |  |
| 𝜏²-Bench Telecom | Agents | 95.6% | Agentic Tool Use |  |
| 𝜏²-Bench Retail | Agents | 77.9% | Agentic Tool Use |  |
| GDPval-AA Elo | Agents | 1232 | Office Tasks (Artificial Analysis) |  |
| Finance Agent | Agents | 56.6% | Agentic Financial Analysis |  |
| Code DesignArena | Design | 1236 |  | https://www.designarena.ai/leaderboard/code |
| Toolathlon | Agents | 37.0% | Benchmark to assess language agents' general tool use in realistic environments. | https://toolathlon.xyz/introduction |

## Model Links

| Title | URL |
| --- | --- |
| Release | https://openai.com/index/gpt-5-1/ |