---
title: "Gemma 4 31B Benchmarks - RankedAGI"
description: "Detailed benchmark and metadata record for Gemma 4."
source: "https://rankedagi.com/models/gemma-4-31b"
---

# Gemma 4

| Field | Value |
| --- | --- |
| Organization | Google |
| License | Open Source |
| Type | Thinking |
| Size | 31B |
| Version | Latest |
| Released | 2026-04-02 |
| Last updated | 2026-05-04T00:15:12.199Z |

## Benchmarks

| Benchmark | Category | Value | Description | Source |
| --- | --- | --- | --- | --- |
| RankedAGI Coding | coding | 61.3% | RankedAGI Coding Score |  |
| SWEBench Pro | coding | 35.7% | Diverse Agentic Coding |  |
| SWEBench Multilingual | coding | 51.7% |  |  |
| SWEBench Verified | coding | 80.9% | Agentic Coding | https://www.swebench.com/index.html |
| Terminal-Bench 2.0 | coding | 42.9% | Agentic Terminal Coding | https://www.tbench.ai/leaderboard/terminal-bench/2.0 |
| RankedAGI Agentic | Agents | 51.5% | RankedAGI Agentic Score |  |
| Livebench Coding 26.1 | coding | 60.3% | Livebench Coding 26.01.08 | https://livebench.ai/#/?Coding=a&sort=Coding+Average&variants=true&highunseenbias=true |
| LiveBench Agentic Coding 26.1 | coding | 40.0% |  | https://livebench.ai/#/?Agentic+Coding=a&sort=Agentic+Coding+Average&variants=true&highunseenbias=true |
| SvelteBench | coding | 100.0% | SvelteBench - Benchmark for Svelte | https://khromov.github.io/svelte-bench/benchmark-results-merged.html |
| LiveCodeBench v6 | coding | 80.0% | LiveCodeBench v6 - Evaluation of Large Language Models for Code |  |
| RankedAGI Reasoning | reasoning | 59.1% | RankedAGI Reasoning Score |  |
| Humanity's Last Exam | reasoning | 19.5% | Multidisciplinary Reasoning (no tools) |  |
| GPQA Diamond | reasoning | 84.3% | Generalized Prefix Question Answering Score (Reasoning) PhD Level Reasoning |  |
| AIME 2026 | math | 89.2% | AIME 2026 Competition Math | https://matharena.ai/?comp=aime--aime_2026&view=problem |
| MMLU Pro | knowledge | 85.2% | Graduate-level visual problem-solving |  |
| RankedAGI Math | math | 71.1% | RankedAGI Math Score |  |
| RankedAGI Overall | general | 56.1% | Overall RankedAGI score |  |

## Model Links

| Title | URL |
| --- | --- |
| Blog | https://blog.google/innovation-and-ai/technology/developers-tools/gemma-4/ |
| DeepMind | https://deepmind.google/models/gemma/gemma-4/ |