# MMLU-ProX leaderboard

Multilingual benchmark

> Every figure below is reproduced as its upstream source published it: nothing is modelled, estimated, interpolated or converted. `Unavailable` means no source published the value — it is never a zero. Each value carries its evidence state and the date it was observed.

Page: https://modelchoice.dev/leaderboards/benchmarks/multilingual-mmlu-pro-x

Every model the catalog carries a published MMLU-ProX value for, ranked by that value.

## Benchmark record

| Field | Value |
| --- | --- |
| Category | Multilingual |
| Measure | Multilingual multiple choice |
| Tasks | Multilingual professional QA |
| Difficulty | Professional multilingual |
| Published by | [MMLU-ProX: A Multilingual Benchmark for Advanced Large Language Model Evaluation](https://arxiv.org/abs/2503.10497) |

A multilingual extension of professional-level academic evaluation across many languages.

## MMLU-ProX ranking

17 models with a published MMLU-ProX value, ordered by that value, highest first. Models the source has not scored on this benchmark are not listed — they are unmeasured, not last.

| Rank | Model | Provider | Multilingual multiple choice | Evidence |
| --- | --- | --- | --- | --- |
| 1 | [Qwen3.7 Max](https://modelchoice.dev/models/qwen3-7-max) | Alibaba | 87 | Observed 2026-11-21 · source benchlm:models |
| 2 | [Claude Opus 4.5](https://modelchoice.dev/models/claude-opus-4-5) | Anthropic | 85.7 | Observed 2026-11-21 · source benchlm:models |
| 3 | [Qwen3.7 Plus](https://modelchoice.dev/models/qwen3-7-plus) | Alibaba | 85.4 | Observed 2026-11-21 · source benchlm:models |
| 4 | [Qwen3.5 397B](https://modelchoice.dev/models/qwen3-5-397b) | Alibaba | 84.7 | Observed 2026-11-21 · source benchlm:models |
| 4 | [Qwen3.6 Plus](https://modelchoice.dev/models/qwen3-6-plus) | Alibaba | 84.7 | Observed 2026-11-21 · source benchlm:models |
| 6 | [GLM-5](https://modelchoice.dev/models/glm-5) | Z.AI | 83.1 | Observed 2026-11-21 · source benchlm:models |
| 7 | [Nemotron 3 Ultra](https://modelchoice.dev/models/nemotron-3-ultra-500b) | NVIDIA | 83 | Observed 2026-11-21 · source benchlm:models |
| 8 | [Kimi K2.5](https://modelchoice.dev/models/kimi-k2-5) | Moonshot AI | 82.3 | Observed 2026-11-21 · source benchlm:models |
| 9 | [Qwen3.5-122B-A10B](https://modelchoice.dev/models/qwen3-5-122b-a10b) | Alibaba | 82.2 | Observed 2026-11-21 · source benchlm:models |
| 9 | [Qwen3.5-27B](https://modelchoice.dev/models/qwen3-5-27b) | Alibaba | 82.2 | Observed 2026-11-21 · source benchlm:models |
| 11 | [Qwen3 235B 2507 (Reasoning)](https://modelchoice.dev/models/qwen3-235b-2507-reasoning) | Alibaba | 81 | Last good 2026-11-18 · source benchlm:models |
| 11 | [Qwen3.5-35B-A3B](https://modelchoice.dev/models/qwen3-5-35b-a3b) | Alibaba | 81 | Observed 2026-11-21 · source benchlm:models |
| 13 | [Qwen3 235B 2507](https://modelchoice.dev/models/qwen3-235b-2507) | Alibaba | 79.4 | Observed 2026-11-21 · source benchlm:models |
| 14 | [GPT-4.1](https://modelchoice.dev/models/gpt-4-1) | OpenAI | 72.7 | Observed 2026-11-21 · source benchlm:models |
| 15 | [DeepSeek V3 0324](https://modelchoice.dev/models/deepseek-v3-0324) | DeepSeek | 70.5 | Observed 2026-11-21 · source benchlm:models |
| 16 | [GPT-4o](https://modelchoice.dev/models/gpt-4o) | OpenAI | 61.1 | Observed 2026-11-21 · source benchlm:models |
| 17 | [Phi-4](https://modelchoice.dev/models/phi-4) | Microsoft | 49.9 | Observed 2026-11-21 · source benchlm:models |

Rows are ordered by the value the source published, highest first. The source does not state whether a higher value is the better result, so this document does not either: for a benchmark that measures a rate of failure, read the table from the bottom.
