# MMMLU leaderboard

Knowledge 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/knowledge-mmmlu

Every model the catalog carries a published MMMLU value for, ranked by that value.

## Benchmark record

| Field | Value |
| --- | --- |
| Category | Knowledge |
| Measure | Exact match |
| Tasks | Multilingual academic QA |
| Difficulty | Broad multilingual knowledge |
| Published by | [MMMLU](https://huggingface.co/datasets/openai/MMMLU) |

A multilingual MMLU-style benchmark reported in provider evaluation tables.

## MMMLU ranking

15 models with a published MMMLU 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 | Exact match | Evidence |
| --- | --- | --- | --- | --- |
| 1 | [Interfaze Beta](https://modelchoice.dev/models/interfaze-beta) | Interfaze | 90.9 | Observed 2026-11-21 · source benchlm:models |
| 2 | [Qwen3.7 Max](https://modelchoice.dev/models/qwen3-7-max) | Alibaba | 90.3 | Observed 2026-11-21 · source benchlm:models |
| 3 | [Qwen3.7 Plus](https://modelchoice.dev/models/qwen3-7-plus) | Alibaba | 89.0 | Observed 2026-11-21 · source benchlm:models |
| 4 | [Claude 4 Opus Thinking](https://modelchoice.dev/models/claude-4-opus-thinking) | Anthropic | 88.8 | Observed 2026-11-21 · source benchlm:models |
| 5 | [Claude 4 Opus](https://modelchoice.dev/models/claude-4-opus) | Anthropic | 87.4 | Observed 2026-11-21 · source benchlm:models |
| 6 | [K-EXAONE 2.0](https://modelchoice.dev/models/k-exaone-2-0) | LG AI Research | 86.6 | Observed 2026-11-21 · source benchlm:models |
| 7 | [Claude 3.7 Sonnet Thinking](https://modelchoice.dev/models/claude-3-7-sonnet-thinking) | Anthropic | 86.1 | Observed 2026-11-21 · source benchlm:models |
| 8 | [Qwen3 235B-A22B (Reasoning)](https://modelchoice.dev/models/qwen3-235b-a22b-reasoning) | Alibaba | 84.3 | Observed 2026-11-21 · source benchlm:models |
| 9 | [Gemma 4 12B](https://modelchoice.dev/models/gemma-4-12b) | Google | 83.4 | Observed 2026-11-21 · source benchlm:models |
| 10 | [Claude 3.7 Sonnet](https://modelchoice.dev/models/claude-3-7-sonnet) | Anthropic | 83.2 | Observed 2026-11-21 · source benchlm:models |
| 11 | [QwQ-32B](https://modelchoice.dev/models/qwq-32b) | Alibaba | 80.9 | Observed 2026-11-21 · source benchlm:models |
| 12 | [Qwen3 32B (Reasoning)](https://modelchoice.dev/models/qwen3-32b-reasoning) | Alibaba | 80.6 | Observed 2026-11-21 · source benchlm:models |
| 13 | [Qwen3 235B-A22B](https://modelchoice.dev/models/qwen3-235b-a22b) | Alibaba | 79.8 | Observed 2026-11-21 · source benchlm:models |
| 14 | [Qwen3 32B](https://modelchoice.dev/models/qwen3-32b) | Alibaba | 76.5 | Observed 2026-11-21 · source benchlm:models |
| 15 | [Phi-3.5-mini](https://modelchoice.dev/models/phi-3-5-mini) | Microsoft | 55.4 | 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.
