# MLVU (M-Avg) leaderboard

Multimodal & Grounded 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/multimodal-grounded-mlvu-avg

MLVU mean average. Every model the catalog carries a published MLVU (M-Avg) value for, ranked by that value.

## Benchmark record

| Field | Value |
| --- | --- |
| Category | Multimodal & Grounded |
| Measure | Video QA and understanding |
| Tasks | General video understanding |
| Difficulty | Broad multimodal video reasoning |
| Published by | [Qwen3.6 launch benchmarks](https://qwen.ai/blog?id=qwen3.6) |

A multi-task video understanding benchmark averaged across MLVU categories.

## MLVU (M-Avg) ranking

10 models with a published MLVU (M-Avg) 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 | Video QA and understanding | Evidence |
| --- | --- | --- | --- | --- |
| 1 | [Qwen3.8 Max](https://modelchoice.dev/models/qwen3-8-max) | Alibaba | 90.8 | Observed 2026-11-21 · source benchlm:models |
| 2 | [Qwen3.7 Plus](https://modelchoice.dev/models/qwen3-7-plus) | Alibaba | 87.4 | Observed 2026-11-21 · source benchlm:models |
| 3 | [Qwen3.5 397B](https://modelchoice.dev/models/qwen3-5-397b) | Alibaba | 86.7 | Observed 2026-11-21 · source benchlm:models |
| 4 | [Qwen3.6-27B](https://modelchoice.dev/models/qwen3-6-27b) | Alibaba | 86.6 | Observed 2026-11-21 · source benchlm:models |
| 5 | [Qwen3.6-35B-A3B](https://modelchoice.dev/models/qwen3-6-35b-a3b) | Alibaba | 86.2 | Observed 2026-11-21 · source benchlm:models |
| 6 | [GPT-5.2](https://modelchoice.dev/models/gpt-5-2) | OpenAI | 85.6 | Observed 2026-11-21 · source benchlm:models |
| 7 | [Kimi K2.5](https://modelchoice.dev/models/kimi-k2-5) | Moonshot AI | 85.0 | Observed 2026-11-21 · source benchlm:models |
| 8 | [Gemini 3 Pro](https://modelchoice.dev/models/gemini-3-pro) | Google | 83.0 | Observed 2026-11-21 · source benchlm:models |
| 9 | [Claude Opus 4.5](https://modelchoice.dev/models/claude-opus-4-5) | Anthropic | 81.7 | Observed 2026-11-21 · source benchlm:models |
| 10 | [LFM3-VL-2B](https://modelchoice.dev/models/lfm3-vl-2b) | LiquidAI | 71.3 | 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.
