---
title: "Mistral Nemo 12B Benchmarks - RankedAGI"
description: "Detailed benchmark and metadata record for Mistral Nemo."
source: "https://rankedagi.com/models/mistral-nemo-12b"
---

# Mistral Nemo

| Field | Value |
| --- | --- |
| Organization | Mistral |
| License | Proprietary |
| Size | 12B |
| Version | Latest |
| Released | 2024-07-24 |
| Context window | 128K |
| Knowledge cutoff | 2024-04-01 |
| Input cost per million tokens | $0.15 |
| Output cost per million tokens | $0.15 |
| Last updated | 2025-04-16 22:14:46.146909+00 |

## Benchmarks

| Benchmark | Category | Value | Description | Source |
| --- | --- | --- | --- | --- |
| RankedAGI Coding | coding | 24.8% | RankedAGI Coding Score |  |
| RankedAGI Agentic | Agents | 29.4% | RankedAGI Agentic Score |  |
| LiveBench Coding Score (old) | coding | 28.7% | LiveBench Coding Score old version |  |
| RankedAGI Reasoning | reasoning | 30.8% | RankedAGI Reasoning Score |  |
| GPQA Diamond | reasoning | 33.0% | Generalized Prefix Question Answering Score (Reasoning) PhD Level Reasoning |  |
| MMLU Pro | knowledge | 44.8% | Graduate-level visual problem-solving |  |
| MMLU | knowledge | 68.0% | Image Reasoning |  |
| Hughes Hallucination Evaluation | safety | 11.2% | 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 | 32.0% | LiveBench Average Score old version |  |
| LiveBench Data Analysis | general | 33.4% | LiveBench Data Analysis Score | https://livebench.ai/ |
| LiveBench Language | general | 14.1% | LiveBench Language Score | https://livebench.ai/ |
| Artificial Analysis Quality Index | general | 52 | Artificial Analysis Quality Index (third-party composite, deprecated) |  |
| RankedAGI Math | math | 49.4% | RankedAGI Math Score |  |
| RankedAGI Overall | general | 35.8% | Overall RankedAGI score |  |