---
title: "Gemini 2.5 Pro Benchmarks - RankedAGI"
description: "Detailed benchmark and metadata record for Gemini 2.5 Pro."
source: "https://rankedagi.com/models/gemini-2.5-pro"
---

# Gemini 2.5 Pro

| Field | Value |
| --- | --- |
| Organization | Google |
| License | Proprietary |
| Version | Latest |
| Released | 2025-06-05 |
| Context window | 1M |
| Knowledge cutoff | 2025-01-01 |
| Input cost per million tokens | $1.25 |
| Output cost per million tokens | $10 |
| Last updated | 2026-06-17T19:00:49.160Z |

## Benchmarks

| Benchmark | Category | Value | Description | Source |
| --- | --- | --- | --- | --- |
| RankedAGI Coding | coding | 53.4% | RankedAGI Coding Score |  |
| SWEBench Verified | coding | 67.2% | Agentic Coding | https://www.swebench.com/index.html |
| RankedAGI Agentic | Agents | 44.4% | RankedAGI Agentic Score |  |
| SvelteBench | coding | 85.6% | SvelteBench - Benchmark for Svelte | https://khromov.github.io/svelte-bench/benchmark-results-merged.html |
| LiveCodeBench v6 | coding | 69.0% | LiveCodeBench v6 - Evaluation of Large Language Models for Code |  |
| LiveBench Coding 25.5 | coding | 70.7% | LiveBench Coding Score 2025-05-30 |  |
| LiveCodeBench v5 | coding | 69.0% | LiveCodeBench - Evaluation of Large Language Models for Code |  |
| ChatArena (LMSYS) | coding | 1496 | ChatArena (LMSYS) Coding ELO Score with Style Control |  |
| Aider Polyglot | coding | 83.1% | Aider Polyglot Code Completion Benchmark |  |
| RankedAGI Reasoning | reasoning | 59.7% | RankedAGI Reasoning Score |  |
| Humanity's Last Exam | reasoning | 21.6% | Multidisciplinary Reasoning (no tools) |  |
| GPQA Diamond | reasoning | 86.4% | Generalized Prefix Question Answering Score (Reasoning) PhD Level Reasoning |  |
| LiveBench Reasoning 25.5 | reasoning | 93.7% | LiveBench Reasoning Score 2025-05-30 |  |
| Text Arena | general | 1470 | ChatArena (LMSYS) ELO Score | https://arena.ai/leaderboard/text |
| AIME 2025 | math | 88.0% | AIME 2025 Competition Math |  |
| Vending Bench 2 | Agents | $573.64 | 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 |
| LiveBench Math Score | math | 83.3% | LiveBench Math Score 25-05 |  |
| MMLU | knowledge | 89.2% | Image Reasoning |  |
| MMMU | imaging | 82.0% | Multimodal Understanding College-level visual problem-solving |  |
| LiveBench IF 25.5 | instruction-following | 78.5% | LiveBench Instruction Following Score 2025-05-30 |  |
| LiveBench Average 25.5 | general | 69.4% | LiveBench Average Score 2025-05-30 |  |
| LiveBench Agentic Coding 25.5 | coding | 13.3% | LiveBench Agentic Coding Score 2025-05-30 | https://livebench.ai/ |
| RankedAGI Math | math | 66.6% | RankedAGI Math Score |  |
| RankedAGI Overall | general | 53.1% | Overall RankedAGI score |  |
| GDPval-AA Elo | Agents | 909 | Office Tasks (Artificial Analysis) |  |
| SvelteBench old | coding | 81.1% | SvelteBench - Benchmark for Svelte (Old v1) | https://khromov.github.io/svelte-bench/v1/v1-benchmark-results-merged.html |
| Code DesignArena | Design | 1204 |  | https://www.designarena.ai/leaderboard/code |
| Toolathlon | Agents | 10.5% | Benchmark to assess language agents' general tool use in realistic environments. | https://toolathlon.xyz/introduction |

## Model Links

| Title | URL |
| --- | --- |
| Release | https://blog.google/products/gemini/gemini-2-5-pro-latest-preview/ |