---
title: "MMMU - Benchmark Evaluation - FinanceBenchmark"
description: "Massive Multi-discipline Multimodal Understanding and Reasoning benchmark for expert AGI."
canonical: "https://financebenchmark.ai/benchmarks/mmmu"
type: "text/markdown"
---
# MMMU

> Massive Multi-discipline Multimodal Understanding and Reasoning benchmark for expert AGI.

## Table of Contents
- [1. Specifications & Metadata](#specifications)
- [2. Model Rankings on this Benchmark](#rankings)
- [3. Source Attribution & Citation](#attribution)

## 1. Specifications & Metadata {#specifications}

- **Slug:** `mmmu`
- **Domain Categories:** documentQA, numerical
- **Composite Weight:** 10 (Tier 3)
- **Task Count:** 11,500 tasks
- **Source / Publisher:** arXiv:2311.16502
- **Research Paper:** [https://arxiv.org/abs/2311.16502](https://arxiv.org/abs/2311.16502)
- **arXiv ID:** [arXiv:2311.16502](https://arxiv.org/abs/2311.16502)

## 2. Model Rankings on this Benchmark {#rankings}

| Rank | Model | Organization | Overall | Eval Date | Source |
|:----:|:------|:-------------|:---:|:---------:|:------:|
| 1 | [Claude Opus 5](https://financebenchmark.ai/models/claude-opus-5.md) | Anthropic | **89.9** | 2026-07 | [Ref](https://vals.ai) |
| 2 | [Claude Fable 5](https://financebenchmark.ai/models/claude-fable-5.md) | Anthropic | **89.3** | 2026-06 | [Ref](https://vals.ai) |
| 3 | [GPT-5.6 Sol](https://financebenchmark.ai/models/gpt-5-6-sol.md) | OpenAI | **88.8** | 2026-07 | [Ref](https://vals.ai) |
| 4 | [Kimi K3](https://financebenchmark.ai/models/kimi-k3.md) | Moonshot AI | **88.2** | 2026-07 | [Ref](https://vals.ai) |
| 5 | [Qwen 3.8 Max](https://financebenchmark.ai/models/qwen-3-8-max.md) | Alibaba | **88.0** | 2026-08 | [Ref](https://vals.ai) |
| 6 | [Gemini 3.6 Flash](https://financebenchmark.ai/models/gemini-3-6-flash.md) | Google | **86.7** | 2026-07 | [Ref](https://vals.ai) |
| 7 | [Muse Spark 1.1](https://financebenchmark.ai/models/muse-spark-1-1.md) | Meta | **86.6** | 2026-07 | [Ref](https://vals.ai) |
| 8 | [GPT-5.6 Terra](https://financebenchmark.ai/models/gpt-5-6-terra.md) | OpenAI | **86.5** | 2026-07 | [Ref](https://vals.ai) |
| 9 | [Muse Spark 1.2](https://financebenchmark.ai/models/muse-spark-1-2.md) | Meta | **86.1** | 2026-08 | [Ref](https://vals.ai) |
| 10 | [GPT-5.6 Luna](https://financebenchmark.ai/models/gpt-5-6-luna.md) | OpenAI | **85.0** | 2026-07 | [Ref](https://vals.ai) |
| 11 | [Gemini 3.5 Flash Lite](https://financebenchmark.ai/models/gemini-3-5-flash-lite.md) | Google | **83.6** | 2026-07 | [Ref](https://vals.ai) |
| 12 | [Claude Sonnet 5](https://financebenchmark.ai/models/claude-sonnet-5.md) | Anthropic | **83.0** | 2026-06 | [Ref](https://vals.ai) |
| 13 | [Inkling](https://financebenchmark.ai/models/inkling.md) | Thinking Machines | **78.5** | 2026-07 | [Ref](https://vals.ai) |
| 14 | [Grok 4.5](https://financebenchmark.ai/models/grok-4-5.md) | xAI | **61.8** | 2026-07 | [Ref](https://vals.ai) |

## 3. Source Attribution & Citation {#attribution}

All scores for MMMU are derived directly from published literature or reproducible evaluation harnesses.
To submit updated evaluations, email [submit@financebenchmark.ai](mailto:submit@financebenchmark.ai).