# MathVision 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://modelscale.dev/leaderboards/benchmarks/multimodal-grounded-math-vision

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

## Benchmark record

| Field | Value |
| --- | --- |
| Category | Multimodal & Grounded |
| Measure | Image + math reasoning |
| Tasks | Visually grounded math problems |
| Difficulty | Advanced multimodal mathematics |
| Published by | [Qwen3.6 launch benchmarks](https://qwen.ai/blog?id=qwen3.6) |

A visual mathematics benchmark that tests whether a model can solve math problems grounded in diagrams, equations, figures, and other visual inputs.

## MathVision ranking

25 models with a published MathVision 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 | Image + math reasoning | Evidence |
| --- | --- | --- | --- | --- |
| 1 | [Qwen3.8 Max](https://modelscale.dev/models/qwen3-8-max) | Alibaba | 95.2 | Observed 2026-11-21 · source benchlm:models |
| 2 | [Kimi K3](https://modelscale.dev/models/kimi-3) | Moonshot AI | 94.3 | Observed 2026-11-21 · source benchlm:models |
| 3 | [Inkling 2 Small](https://modelscale.dev/models/inkling-2-small) | Thinking Machines Lab | 92.8 | Observed 2026-11-21 · source benchlm:models |
| 4 | [Seed 2.1 Pro](https://modelscale.dev/models/seed-2-1-pro) | ByteDance | 92.6 | Observed 2026-11-21 · source benchlm:models |
| 5 | [Qwen3.8-Omni-Flash](https://modelscale.dev/models/qwen3-8-omni-flash) | Alibaba | 91.8 | Observed 2026-11-21 · source benchlm:models |
| 6 | [Qwen3.8-Flash-Next](https://modelscale.dev/models/qwen3-8-flash-next) | Alibaba | 90.6 | Observed 2026-11-21 · source benchlm:models |
| 7 | [Qwen3.7 Plus](https://modelscale.dev/models/qwen3-7-plus) | Alibaba | 90.3 | Observed 2026-11-21 · source benchlm:models |
| 8 | [Seed 2.1 Turbo](https://modelscale.dev/models/seed-2-1-turbo) | ByteDance | 90.1 | Observed 2026-11-21 · source benchlm:models |
| 9 | [Qwen3.8-27B](https://modelscale.dev/models/qwen3-8-27b) | Alibaba | 90.0 | Observed 2026-11-21 · source benchlm:models |
| 10 | [Inkling 2 Mini](https://modelscale.dev/models/inkling-2-mini) | Thinking Machines Lab | 89.0 | Observed 2026-11-21 · source benchlm:models |
| 11 | [Qwen3.5 397B](https://modelscale.dev/models/qwen3-5-397b) | Alibaba | 88.6 | Observed 2026-11-21 · source benchlm:models |
| 12 | [Qwen3.6 Plus](https://modelscale.dev/models/qwen3-6-plus) | Alibaba | 88.0 | Observed 2026-11-21 · source benchlm:models |
| 13 | [dots3-note Preview](https://modelscale.dev/models/dots3-note-preview) | Dots Studio | 87.7 | Observed 2026-11-21 · source benchlm:models |
| 14 | [Kimi K2.6](https://modelscale.dev/models/kimi-2-6) | Moonshot AI | 87.4 | Observed 2026-11-21 · source benchlm:models |
| 15 | [Gemini 3 Pro](https://modelscale.dev/models/gemini-3-pro) | Google | 86.6 | Observed 2026-11-21 · source benchlm:models |
| 16 | [Qwen3.5-122B-A10B](https://modelscale.dev/models/qwen3-5-122b-a10b) | Alibaba | 86.2 | Observed 2026-11-21 · source benchlm:models |
| 17 | [Qwen3.5-27B](https://modelscale.dev/models/qwen3-5-27b) | Alibaba | 86.0 | Observed 2026-11-21 · source benchlm:models |
| 18 | [Kimi K2.5](https://modelscale.dev/models/kimi-k2-5) | Moonshot AI | 84.2 | Observed 2026-11-21 · source benchlm:models |
| 19 | [Qwen3.5-35B-A3B](https://modelscale.dev/models/qwen3-5-35b-a3b) | Alibaba | 83.9 | Observed 2026-11-21 · source benchlm:models |
| 20 | [GPT-5.2](https://modelscale.dev/models/gpt-5-2) | OpenAI | 83.0 | Observed 2026-11-21 · source benchlm:models |
| 21 | [Gemma 4 12B](https://modelscale.dev/models/gemma-4-12b) | Google | 79.7 | Observed 2026-11-21 · source benchlm:models |
| 22 | [Nemotron 3.5 Super VL 120B A12B](https://modelscale.dev/models/nemotron-3-5-super-vl-120b-a12b) | NVIDIA | 78.2 | Observed 2026-11-21 · source benchlm:models |
| 23 | [Nemotron 3.5 Super VL 120B A12B NVFP4](https://modelscale.dev/models/nemotron-3-5-super-vl-120b-a12b-nvfp4) | NVIDIA | 77.8 | Observed 2026-11-21 · source benchlm:models |
| 24 | [Claude Opus 4.5](https://modelscale.dev/models/claude-opus-4-5) | Anthropic | 74.3 | Observed 2026-11-21 · source benchlm:models |
| 25 | [LFM3-VL-2B](https://modelscale.dev/models/lfm3-vl-2b) | LiquidAI | 51.6 | 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.
