---
title: "Gemini 3.1 Pro Benchmarks - RankedAGI"
description: "Detailed benchmark and metadata record for Gemini 3.1 Pro."
source: "https://rankedagi.com/models/gemini-3-1-pro"
---

# Gemini 3.1 Pro

| Field | Value |
| --- | --- |
| Organization | Google |
| License | Proprietary |
| Type | Thinking |
| Version | Latest |
| Released | 2026-02-19 |
| Last updated | 2026-05-28T21:32:30.135Z |

## Benchmarks

| Benchmark | Category | Value | Description | Source |
| --- | --- | --- | --- | --- |
| RankedAGI Coding | coding | 80.5% | RankedAGI Coding Score |  |
| SWEBench Pro | coding | 54.2% | Diverse Agentic Coding |  |
| SWEBench Verified | coding | 80.6% | Agentic Coding | https://www.swebench.com/index.html |
| Terminal-Bench 2.0 | coding | 68.5% | Agentic Terminal Coding | https://www.tbench.ai/leaderboard/terminal-bench/2.0 |
| Terminal-Bench 2.1 | coding | 70.7% | Agentic Terminal Coding | https://www.tbench.ai/leaderboard/terminal-bench/2.1 |
| RankedAGI Agentic | Agents | 65.7% | RankedAGI Agentic Score |  |
| BrowseComp | Agents | 85.9% | A benchmark for browsing agents | https://openai.com/index/browsecomp/ |
| Code Arena | coding | 1456 | Code Arena Elo Score | https://arena.ai/leaderboard/code |
| Livebench Coding 26.1 | coding | 76.5% | Livebench Coding 26.01.08 | https://livebench.ai/#/?Coding=a&sort=Coding+Average&variants=true&highunseenbias=true |
| DeepSWE | coding | 10.0% | Measuring frontier coding agents on original, long-horizon engineering tasks | https://deepswe.datacurve.ai/ |
| LiveBench Agentic Coding 26.1 | coding | 65.0% |  | 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 | 91.7% | LiveCodeBench v6 - Evaluation of Large Language Models for Code |  |
| CyberGym | safety | 38.8% |  |  |
| Codeforces ELO Score | coding | 3052 | Codeforces ELO Score |  |
| RankedAGI Reasoning | reasoning | 77.6% | RankedAGI Reasoning Score |  |
| Humanity's Last Exam | reasoning | 44.4% | Multidisciplinary Reasoning (no tools) |  |
| Humanity's Last Exam w/ Tools | reasoning | 51.6% | Multidisciplinary Reasoning (with tools) |  |
| GPQA Diamond | reasoning | 94.3% | Generalized Prefix Question Answering Score (Reasoning) PhD Level Reasoning |  |
| Vending Bench 2 | Agents | $911.21 | 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 |
| MMLU Pro | knowledge | 91.0% | Graduate-level visual problem-solving |  |
| MMMU-Pro | imaging | 80.5% | Multimodal Understanding |  |
| RankedAGI Math | math | 72.3% | RankedAGI Math Score |  |
| RankedAGI Overall | general | 67.3% | Overall RankedAGI score |  |
| ARC AGI 2 | reasoning | 77.1% | Abstract Reasoning Puzzles (Public) |  |
| LiveCodeBench Pro | coding | 82.9% | Competitive Coding |  |
| 𝜏²-Bench Telecom | Agents | 95.6% | Agentic Tool Use |  |
| HealthBench Hard | Health | 20.6% | Open-ended Health Queries |  |
| MedXpertQA Text | Health | 71.5% | Medical Multiple Choice |  |
| MedXpertQA (MM) | Health | 81.3% | Medical Multiple Choice |  |
| DeepSearch QA | Agents | 69.7% | Agentic Search |  |
| GDPval-AA Elo | Agents | 1314 | Office Tasks (Artificial Analysis) |  |
| ZeroBench | general | 29.0% | Multi-step Visual Reasoning |  |
| MCP Atlas | Agents | 69.2% | Scaled Tool Use |  |
| Finance Agent | Agents | 59.7% | Agentic Financial Analysis |  |
| CharXiv Reasoning | Multimodal | 80.2% | Figure Understanding |  |
| Code DesignArena | Design | 1293 |  | https://www.designarena.ai/leaderboard/code |
| Toolathlon | Agents | 48.8% | Benchmark to assess language agents' general tool use in realistic environments. | https://toolathlon.xyz/introduction |
| Tau3 Bench | Agents | 67.1% |  | https://sierra.ai/resources/research/tau-3-bench |

## Model Links

| Title | URL |
| --- | --- |
| Release | https://blog.google/innovation-and-ai/models-and-research/gemini-models/gemini-3-1-pro/ |