---
title: "Gemini 2 Flash Thinking Benchmarks - RankedAGI"
description: "Detailed benchmark and metadata record for Gemini 2 Flash Thinking."
source: "https://rankedagi.com/models/gemini-2-flash-thinking-0121"
---

# Gemini 2 Flash Thinking

| Field | Value |
| --- | --- |
| Organization | Google |
| License | Proprietary |
| Version | Preview |
| Released | 2025-01-21 |
| Context window | 1M |
| Knowledge cutoff | 2024-08-01 |
| Model ID | gemini-2.0-flash-thinking-exp |
| Last updated | 2026-05-04T01:35:41.811Z |

## Benchmarks

| Benchmark | Category | Value | Description | Source |
| --- | --- | --- | --- | --- |
| RankedAGI Coding | coding | 43.5% | RankedAGI Coding Score |  |
| RankedAGI Agentic | Agents | 33.7% | RankedAGI Agentic Score |  |
| ChatArena (LMSYS) | coding | 1290 | ChatArena (LMSYS) Coding ELO Score with Style Control |  |
| LiveBench Coding Score (old) | coding | 53.5% | LiveBench Coding Score old version |  |
| RankedAGI Reasoning | reasoning | 38.9% | RankedAGI Reasoning Score |  |
| Humanity's Last Exam | reasoning | 7.2% | Multidisciplinary Reasoning (no tools) |  |
| GPQA Diamond | reasoning | 74.2% | Generalized Prefix Question Answering Score (Reasoning) PhD Level Reasoning |  |
| Text Arena | general | 1380 | ChatArena (LMSYS) ELO Score | https://arena.ai/leaderboard/text |
| AIME 2025 | math | 53.5% | AIME 2025 Competition Math |  |
| NYT Connections Extended | reasoning | 23.1% | NYT Connections Extended Version | https://github.com/lechmazur/nyt-connections/ |
| Hughes Hallucination Evaluation | safety | 1.8% | 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 Average | general | 66.9% | LiveBench Average Score old version |  |
| LiveBench Coding 25.4 | coding | 35.7% | LiveBench Coding Score 2025-04 | https://livebench.ai/ |
| LiveBench Data Analysis | general | 69.4% | LiveBench Data Analysis Score | https://livebench.ai/ |
| LiveBench Language | general | 42.2% | LiveBench Language Score | https://livebench.ai/ |
| RankedAGI Math | math | 54.9% | RankedAGI Math Score |  |
| RankedAGI Overall | general | 43.4% | Overall RankedAGI score |  |