---
title: "Gemini 2.5 Flash Benchmarks - RankedAGI"
description: "Detailed benchmark and metadata record for Gemini 2.5 Flash."
source: "https://rankedagi.com/models/gemini-2.5-flash-preview-04-17"
---

# Gemini 2.5 Flash

| Field | Value |
| --- | --- |
| Organization | Google |
| License | Proprietary |
| Version | Preview |
| Released | 2025-04-17 |
| Context window | 1M |
| Knowledge cutoff | 2025-01-01 |
| Input cost per million tokens | $0.15 |
| Output cost per million tokens | $0.6 |
| Model ID | gemini-2.5-flash-preview-04-17 |
| Last updated | 2026-05-04T03:43:08.354Z |

## Benchmarks

| Benchmark | Category | Value | Description | Source |
| --- | --- | --- | --- | --- |
| RankedAGI Coding | coding | 48.6% | RankedAGI Coding Score |  |
| RankedAGI Agentic | Agents | 36.1% | RankedAGI Agentic Score |  |
| LiveCodeBench v5 | coding | 63.5% | LiveCodeBench - Evaluation of Large Language Models for Code |  |
| CyberGym | safety | 4.8% |  |  |
| Aider Polyglot | coding | 51.1% | Aider Polyglot Code Completion Benchmark |  |
| RankedAGI Reasoning | reasoning | 47.1% | RankedAGI Reasoning Score |  |
| Humanity's Last Exam | reasoning | 12.1% | Multidisciplinary Reasoning (no tools) |  |
| GPQA Diamond | reasoning | 78.3% | Generalized Prefix Question Answering Score (Reasoning) PhD Level Reasoning |  |
| Text Arena | general | 1400 | ChatArena (LMSYS) ELO Score | https://arena.ai/leaderboard/text |
| AIME 2025 | math | 78.0% | AIME 2025 Competition Math |  |
| AIME 2024 | math | 88.0% | AIME 2024 Competition Math |  |
| MMLU | knowledge | 88.4% | Image Reasoning |  |
| MMMU | imaging | 76.7% | Multimodal Understanding College-level visual problem-solving |  |
| Hughes Hallucination Evaluation | safety | 1.3% | 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 Coding 25.4 | coding | 58.4% | LiveBench Coding Score 2025-04 | https://livebench.ai/ |
| RankedAGI Math | math | 67.3% | RankedAGI Math Score |  |
| RankedAGI Overall | general | 47.5% | Overall RankedAGI score |  |
| GDPval-AA Elo | Agents | 706 | Office Tasks (Artificial Analysis) |  |
| SvelteBench old | coding | 70.0% | SvelteBench - Benchmark for Svelte (Old v1) | https://khromov.github.io/svelte-bench/v1/v1-benchmark-results-merged.html |
| Code DesignArena | Design | 1169 |  | https://www.designarena.ai/leaderboard/code |

## Model Links

| Title | URL |
| --- | --- |
| Release | https://developers.googleblog.com/en/start-building-with-gemini-25-flash/ |