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

# Gemini 2.5 Flash Lite

| Field | Value |
| --- | --- |
| Organization | Google |
| License | Proprietary |
| Version | Latest |
| Released | 2025-06-17 |
| Context window | 1M |
| Knowledge cutoff | 2025-01-01 |
| Input cost per million tokens | $0.1 |
| Output cost per million tokens | $0.4 |
| Last updated | 2026-04-20T06:24:00.465Z |

## Benchmarks

| Benchmark | Category | Value | Description | Source |
| --- | --- | --- | --- | --- |
| RankedAGI Coding | coding | 36.1% | RankedAGI Coding Score |  |
| SWEBench Verified | coding | 42.6% | Agentic Coding | https://www.swebench.com/index.html |
| RankedAGI Agentic | Agents | 27.4% | RankedAGI Agentic Score |  |
| LiveCodeBench v6 | coding | 33.7% | LiveCodeBench v6 - Evaluation of Large Language Models for Code |  |
| Aider Polyglot | coding | 26.7% | Aider Polyglot Code Completion Benchmark |  |
| RankedAGI Reasoning | reasoning | 34.6% | RankedAGI Reasoning Score |  |
| Humanity's Last Exam | reasoning | 5.1% | Multidisciplinary Reasoning (no tools) |  |
| GPQA Diamond | reasoning | 64.6% | Generalized Prefix Question Answering Score (Reasoning) PhD Level Reasoning |  |
| AIME 2025 | math | 49.8% | AIME 2025 Competition Math |  |
| MMLU | knowledge | 81.1% | Image Reasoning |  |
| MMMU | imaging | 72.9% | Multimodal Understanding College-level visual problem-solving |  |
| RankedAGI Math | math | 52.3% | RankedAGI Math Score |  |
| RankedAGI Overall | general | 39.1% | Overall RankedAGI score |  |
| GDPval-AA Elo | Agents | 311 | Office Tasks (Artificial Analysis) |  |

## Model Links

| Title | URL |
| --- | --- |
| Release | https://developers.googleblog.com/en/gemini-2-5-thinking-model-updates/ |